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 2022/05/28 02:24:48 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@2b0e082f39b408f750a9c6f6181a75e8a2e7a0e2)
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 12ac2d4c5 deploying docs (apache/tvm@2b0e082f39b408f750a9c6f6181a75e8a2e7a0e2)
12ac2d4c5 is described below
commit 12ac2d4c5bd8c0bde4c7b3421541b5ba7963b571
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sat May 28 02:24:42 2022 +0000
deploying docs (apache/tvm@2b0e082f39b408f750a9c6f6181a75e8a2e7a0e2)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 -
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 2643 +++++++-------------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 84 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../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 | 3 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 44 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 79 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 7 +-
docs/how_to/compile_models/from_tensorflow.html | 1 -
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 20 +-
docs/how_to/deploy_models/deploy_prequantized.html | 8 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 2642 +++++++------------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 83 +-
.../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 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
.../reference/api/doxygen/arg__info_8h_source.html | 2 +-
docs/reference/api/doxygen/bytecode_8h_source.html | 2 +-
.../api/doxygen/c__runtime__api_8h_source.html | 2 +-
.../api/doxygen/data__layout_8h_source.html | 2 +-
.../api/doxygen/dataflow__pattern_8h_source.html | 2 +-
.../api/doxygen/detail_2broadcast_8h_source.html | 2 +-
.../api/doxygen/detail_2extern_8h_source.html | 2 +-
.../api/doxygen/device__api_8h_source.html | 2 +-
docs/reference/api/doxygen/einsum_8h_source.html | 2 +-
docs/reference/api/doxygen/elemwise_8h_source.html | 2 +-
.../api/doxygen/index__map_8h_source.html | 2 +-
.../api/doxygen/memory__manager_8h_source.html | 2 +-
docs/reference/api/doxygen/ndarray_8h_source.html | 2 +-
.../api/doxygen/nn_2softmax_8h_source.html | 4 +-
.../reference/api/doxygen/operation_8h_source.html | 2 +-
.../reference/api/doxygen/profiling_8h_source.html | 2 +-
.../api/doxygen/ravel__unravel_8h_source.html | 2 +-
.../api/doxygen/shape__tuple_8h_source.html | 2 +-
docs/reference/api/doxygen/tensor_8h_source.html | 2 +-
.../api/doxygen/tensor__type_8h_source.html | 2 +-
docs/reference/api/doxygen/topi_2nn_8h_source.html | 2 +-
.../api/doxygen/topi_2transform_8h_source.html | 24 +-
docs/reference/api/python/auto_scheduler.html | 6 +-
.../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 | 2 +-
docs/tutorial/autotvm_relay_x86.html | 199 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 44 +-
137 files changed, 2579 insertions(+), 4507 deletions(-)
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 33dc14d4b..fa08070c9 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipd71e3628-38c2-4d5a-8075-c0f944682a3a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipcaa497d7-ca8d-4f0a-8874-38be19d8c70d 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 e50f140f1..356d59da9 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ 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]
0%| | 16.0k/41.5M [00:00<07:34, 95.7kB/s]
0%| | 40.0k/41.5M [00:00<05:52, 123kB/s]
0%| | 88.0k/41.5M [00:00<03:39, 198kB/s]
0%| | 184k/41.5M [00:00<02:05, 345kB/s]
1%| | 360k/41.5M [00:00<01:12, 598kB/s]
2%|1 | 728k/41.5M [00:01<00:37, 1.14MB/s]
3%|3 | 1.42M/41.5M [00:01<00:19, 2.18MB/s]
7%|6 | 2.77M/41.5M [00:01<00:08, 4.53MB/s]
9%|9 | 3.91M/41.5M [00:01<00:06, 6.23MB/s]
11%|#1 | 4.62M/41.5M [00:01<00:06, 5.61MB/s]
14%|#3 | 5.77M/41.5M [00:01<00:05, 6.77MB/s]
17%|#6 | 6.98M/41.5M [00:01<00:04, 7.66MB/s]
20%|## | 8.35M/41.5M [00:01<00:03, 9.28MB/s]
22%|##2 | 9.32M/41.5M [00:02<00:04, 8.07MB/s]
25%|##4 | 10.2M/41.5M [00:02<00:04, 7.94MB/s]
27%|##7 | 11.3M/41.5M [00:02<00:03, 8.40MB/s]
31%|### | 12.8M/41.5M [00:02<0
0:03, 10.0MB/s]
33%|###3 | 13.8M/41.5M [00:02<00:03, 8.61MB/s]
35%|###5 | 14.7M/41.5M [00:02<00:03, 8.23MB/s]
38%|###7 | 15.7M/41.5M [00:02<00:03, 8.54MB/s]
41%|####1 | 17.0M/41.5M [00:02<00:02, 9.81MB/s]
43%|####3 | 18.0M/41.5M [00:03<00:02, 8.48MB/s]
46%|####5 | 19.0M/41.5M [00:03<00:02, 8.41MB/s]
49%|####8 | 20.1M/41.5M [00:03<00:02, 8.74MB/s]
52%|#####1 | 21.5M/41.5M [00:03<00:02, 9.94MB/s]
54%|#####4 | 22.4M/41.5M [00:03<00:02, 8.57MB/s]
56%|#####6 | 23.4M/41.5M [00:03<00:02, 8.45MB/s]
59%|#####9 | 24.6M/41.5M [00:03<00:01, 9.04MB/s]
61%|######1 | 25.5M/41.5M [00:04<00:01, 8.94MB/s]
63%|######3 | 26.3M/41.5M [00:04<00:01, 8.40MB/s]
66%|######6 | 27.5M/41.5M [00:04<00:01, 8.91MB/s]
69%|######9 | 28.8M/41.5M [00:04<00:01, 10.2MB/s]
72%|#######1 | 29.8M/41.5M [00:04<00:01, 8.67MB/s]
74%|#######4 | 30.7M/41.5M [00:04<00:01, 8.50MB/s]
77%|###
####6 | 31.9M/41.5M [00:04<00:01, 8.82MB/s]
80%|######## | 33.2M/41.5M [00:04<00:00, 10.0MB/s]
82%|########2 | 34.2M/41.5M [00:05<00:00, 8.62MB/s]
85%|########4 | 35.1M/41.5M [00:05<00:00, 8.44MB/s]
88%|########7 | 36.3M/41.5M [00:05<00:00, 8.81MB/s]
90%|######### | 37.5M/41.5M [00:05<00:00, 9.63MB/s]
93%|#########2| 38.4M/41.5M [00:05<00:00, 8.28MB/s]
95%|#########5| 39.5M/41.5M [00:05<00:00, 8.65MB/s]
98%|#########8| 40.7M/41.5M [00:05<00:00, 8.96MB/s]
100%|##########| 41.5M/41.5M [00:05<00:00, 7.38MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:48, 92.8kB/s]
0%| | 48.0k/41.5M [00:00<04:55, 147kB/s]
0%| | 96.0k/41.5M [00:00<03:30, 207kB/s]
0%| | 192k/41.5M [00:00<02:05, 344kB/s]
1%| | 392k/41.5M [00:00<01:07, 637kB/s]
2%|1 | 784k/41.5M [00:01<00:35, 1.19MB/s]
4%|3 | 1.54M/41.5M [00:01<00:18, 2.30MB/s]
7%|7 | 3.00M/41.5M [00:01<00:09, 4.31MB/s]
11%|# | 4.47M/41.5M [00:01<00:06, 5.68MB/s]
14%|#4 | 5.94M/41.5M [00:01<00:05, 6.61MB/s]
18%|#7 | 7.41M/41.5M [00:01<00:04, 7.24MB/s]
21%|##1 | 8.88M/41.5M [00:02<00:04, 7.68MB/s]
25%|##4 | 10.3M/41.5M [00:02<00:04, 7.98MB/s]
28%|##8 | 11.8M/41.5M [00:02<00:03, 8.20MB/s]
32%|###2 | 13.3M/41.5M [00:02<00:03, 8.34MB/s]
36%|###5 | 14.8M/41.5M [00:02<00:03, 8.44MB/s]
39%|###9 | 16.2M/41.5M [00:03<0
0:03, 8.51MB/s]
43%|####2 | 17.7M/41.5M [00:03<00:02, 8.56MB/s]
46%|####6 | 19.2M/41.5M [00:03<00:02, 8.60MB/s]
50%|####9 | 20.6M/41.5M [00:03<00:02, 8.62MB/s]
53%|#####3 | 22.1M/41.5M [00:03<00:02, 8.63MB/s]
57%|#####6 | 23.6M/41.5M [00:03<00:02, 8.64MB/s]
60%|###### | 25.0M/41.5M [00:04<00:01, 8.65MB/s]
64%|######3 | 26.5M/41.5M [00:04<00:01, 8.66MB/s]
67%|######7 | 28.0M/41.5M [00:04<00:01, 8.67MB/s]
71%|####### | 29.4M/41.5M [00:04<00:01, 8.67MB/s]
74%|#######4 | 30.9M/41.5M [00:04<00:01, 8.67MB/s]
78%|#######8 | 32.4M/41.5M [00:04<00:01, 8.68MB/s]
82%|########1 | 33.8M/41.5M [00:05<00:00, 8.68MB/s]
85%|########5 | 35.3M/41.5M [00:05<00:00, 8.67MB/s]
89%|########8 | 36.8M/41.5M [00:05<00:00, 8.66MB/s]
92%|#########2| 38.2M/41.5M [00:05<00:00, 8.67MB/s]
96%|#########5| 39.7M/41.5M [00:05<00:00, 8.67MB/s]
99%|#########9| 41.2M/41.5M [00:06<00:00, 8.67MB/s]
100%|###
#######| 41.5M/41.5M [00:06<00:00, 7.21MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index caa0b9eef..69eb795a4 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -210,7 +210,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 10.631 seconds)
+ **Total running time of the script:** ( 1 minutes 5.233 seconds)
.. _sphx_glr_download_how_to_compile_models_from_paddle.py:
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 2c83f86e2..32e5475fe 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ 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]
42%|####2 | 18.8M/44.7M [00:00<00:00, 197MB/s]
96%|#########6| 42.9M/44.7M [00:00<00:00, 230MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 226MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
10%|9 | 4.42M/44.7M [00:00<00:00, 46.3MB/s]
20%|#9 | 8.84M/44.7M [00:00<00:00, 43.2MB/s]
75%|#######5 | 33.5M/44.7M [00:00<00:00, 138MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 132MB/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 6041af8b0..fa7a92713 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -379,11 +379,6 @@ Run the corresponding model on tensorflow
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.823 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 e47681413..3f4edfe47 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
@@ -5,15 +5,15 @@
Computation times
=================
-**05:28.427** total execution time for **how_to_compile_models** files:
+**05:12.664** total execution time for **how_to_compile_models** files:
-- **01:10.631**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:02.823**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.914**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:31.143**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.352**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.475**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:22.076**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:19.245**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.158**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.609**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:05.233**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **00:59.222**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:57.204**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:30.012**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:23.849**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.845**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.755**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:18.831**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.279**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.433**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
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 312db1690..b77b292e0 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
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 18.0075 16.6107 27.2934 16.4056 3.2379
+ 16.1771 16.1997 16.3861 15.9035 0.1371
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 b62ed2914..7e80cb0d1 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
@@ -108,7 +108,7 @@ 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]
2%|2 | 3.84M/170M [00:00<00:04, 40.1MB/s]
5%|4 | 7.66M/170M [00:00<00:04, 38.0MB/s]
14%|#3 | 23.8M/170M [00:00<00:01, 95.9MB/s]
27%|##7 | 46.0M/170M [00:00<00:00, 149MB/s]
39%|###9 | 66.3M/170M [00:00<00:00, 172MB/s]
53%|#####2 | 89.2M/170M [00:00<00:00, 195MB/s]
64%|######3 | 108M/170M [00:00<00:00, 190MB/s]
74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
89%|########9 | 151M/170M [00:00<00:00, 204MB/s]
100%|##########| 170M/170M [00:01<00:00, 176MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
11%|# | 17.9M/170M [00:00<00:00, 187MB/s]
25%|##5 | 43.0M/170M [00:00<00:00, 232MB/s]
40%|#### | 68.0M/170M [00:00<00:00, 245MB/s]
54%|#####3 | 91.4M/170M [00:00<00:00, 227MB/s]
68%|######7 | 115M/170M [00:00<00:00, 234MB/s]
81%|########1 | 138M/170M [00:00<00:00, 228MB/s]
95%|#########5| 162M/170M [00:00<00:00, 235MB/s]
100%|##########| 170M/170M [00:00<00:00, 233MB/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').
@@ -262,7 +262,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 20.035 seconds)
+ **Total running time of the script:** ( 3 minutes 5.941 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 ee641a660..f2e650b98 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ 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]
39%|###8 | 5.25M/13.6M [00:00<00:00, 52.1MB/s]
80%|#######9 | 10.8M/13.6M [00:00<00:00, 55.4MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 37.0MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
@@ -353,7 +353,7 @@ 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)
- 90.4921 90.4585 91.1791 90.2927 0.1491
+ 90.5256 90.5225 90.8171 90.1770 0.0912
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.494 seconds)
+ **Total running time of the script:** ( 1 minutes 8.504 seconds)
.. _sphx_glr_download_how_to_deploy_models_deploy_prequantized.py:
diff --git a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
index 4b2e32e43..ddd3091b6 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
@@ -360,7 +360,7 @@ 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)
- 122.4539 122.4579 123.6657 121.7679 0.3363
+ 116.3068 116.2124 118.1089 115.3573 0.5102
@@ -394,7 +394,7 @@ 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 55.501 seconds)
+ **Total running time of the script:** ( 1 minutes 52.976 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 89f68bc26..962918113 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -223,7 +223,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.471 seconds)
+ **Total running time of the script:** ( 1 minutes 6.851 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 56efd215b..c5164a4b1 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
@@ -137,7 +137,7 @@ 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]
2%|2 | 3316/132723 [00:00<00:03, 33158.13KB/s]
8%|7 | 10096/132723 [00:00<00:02, 53532.78KB/s]
13%|#3 | 17895/132723 [00:00<00:01, 64695.56KB/s]
19%|#9 | 25797/132723 [00:00<00:01, 70347.37KB/s]
25%|##5 | 33765/132723 [00:00<00:01, 73710.24KB/s]
31%|###1 | 41531/132723 [00:00<00:01, 75050.72KB/s]
37%|###7 | 49420/132723 [00:00<00:01, 76303.20KB/s]
43%|####3 | 57341/132723 [00:00<00:00, 77224.74KB/s]
49%|####9 | 65264/132723 [00:00<00:00, 77848.51KB/s]
55%|#####5 | 73183/132723 [00:01<00:00, 78256.89KB/s]
61%|######1 | 81117/132723 [00:01<00:00, 78584.92KB/s]
67%|######7 | 88976/132723 [00:01<00:00, 77487.20KB/s]
73%|#######2 | 96729/132723 [00:01<00:00, 77214.03KB/s]
79%|#######8 | 104453/132723 [00:01<00:00, 77181.47KB/s]
85%|########4 | 112387/132723 [00:01<00:00, 77826.14KB/s]
91%|#########
| 120303/132723 [00:01<00:00, 78215.01KB/s]
97%|#########6| 128245/132723 [00:01<00:00, 78570.42KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75253.32KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6979/132723 [00:00<00:01, 69783.08KB/s]
12%|#1 | 15751/132723 [00:00<00:01, 80331.68KB/s]
19%|#8 | 24560/132723 [00:00<00:01, 83869.09KB/s]
25%|##5 | 33449/132723 [00:00<00:01, 85846.76KB/s]
32%|###1 | 42332/132723 [00:00<00:01, 86915.47KB/s]
39%|###8 | 51167/132723 [00:00<00:00, 87402.41KB/s]
45%|####5 | 60029/132723 [00:00<00:00, 87799.72KB/s]
52%|#####1 | 68907/132723 [00:00<00:00, 88110.66KB/s]
59%|#####8 | 77728/132723 [00:00<00:00, 88139.71KB/s]
65%|######5 | 86566/132723 [00:01<00:00, 88211.06KB/s]
72%|#######1 | 95400/132723 [00:01<00:00, 88249.06KB/s]
79%|#######8 | 104275/132723 [00:01<00:00, 88397.94KB/s]
85%|########5 | 113115/132723 [00:01<00:00, 88342.77KB/s]
92%|#########1| 121950/132723 [00:01<00:00, 88062.90KB/s]
99%|#########8| 130760/132723 [00:01<00:00, 88073.14KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 86859.44KB/s]
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 33.935 seconds)
+ **Total running time of the script:** ( 2 minutes 20.665 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 2b4ee51ed..3b0f556ab 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
@@ -5,13 +5,13 @@
Computation times
=================
-**11:10.303** total execution time for **how_to_deploy_models** files:
+**10:25.191** total execution time for **how_to_deploy_models** files:
-- **03:20.035**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:33.935**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:55.501**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:17.471**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:09.494**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:30.928**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.728**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:05.941**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:20.665**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:52.976**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:08.504**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **01:06.851**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **00:28.471**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.602**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.181**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
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 bb8b4bceb..ec74c9f4b 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
@@ -425,7 +425,7 @@ 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.zip5ab718f8-a58c-460e-b325-6f5afcb9fff5 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4aabba12-aeb3-47cb-830c-381cd2f54efd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 5d8e5066a..775cb6231 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
@@ -5,9 +5,9 @@
Computation times
=================
-**00:39.897** total execution time for **how_to_extend_tvm** files:
+**00:37.769** total execution time for **how_to_extend_tvm** files:
-- **00:36.220**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.350**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.108**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.219**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.362**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.205**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.020**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.183**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
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 a7205f451..9fa52aca3 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
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6279us [6279us] (45.53%; 45.53%)
- FoldScaleAxis: 7513us [2us] (54.47%; 54.47%)
- FoldConstant: 7510us [1536us] (54.45%; 99.97%)
- InferType: 5975us [5975us] (43.32%; 79.55%)
+ InferType: 6252us [6252us] (45.55%; 45.55%)
+ FoldScaleAxis: 7472us [2us] (54.45%; 54.45%)
+ FoldConstant: 7470us [1557us] (54.43%; 99.97%)
+ InferType: 5913us [5913us] (43.08%; 79.15%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6086us [6086us] (45.14%; 45.14%)
- FoldScaleAxis: 7397us [2us] (54.86%; 54.86%)
- FoldConstant: 7394us [1538us] (54.84%; 99.97%)
- InferType: 5857us [5857us] (43.44%; 79.20%)
+ InferType: 6009us [6009us] (44.66%; 44.66%)
+ FoldScaleAxis: 7447us [2us] (55.34%; 55.34%)
+ FoldConstant: 7445us [1539us] (55.33%; 99.98%)
+ InferType: 5906us [5906us] (43.89%; 79.33%)
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 35756f42b..e53aaafd5 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
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 40.692116 ms
+ Convolution: 54.099805 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 37623779a..311bf288c 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
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.044295 ms
+ conv2d with tensor core: 6.581543 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 b48e1798f..4d1152850 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019797
- Baseline: 3.581554
+ Numpy running time: 0.018160
+ Baseline: 3.412251
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.332761
+ Opt1: 0.300460
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.348876
+ Opt2: 0.338944
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.135626
+ Opt3: 0.115266
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112655
+ Opt4: 0.110973
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.113771
+ Opt5: 0.112382
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.147764
+ Opt6: 0.145613
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 d48e6deec..4c115477c 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:36.802** total execution time for **how_to_optimize_operators** files:
+**00:34.834** total execution time for **how_to_optimize_operators** files:
-- **00:34.095**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.479**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.228**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.388**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.321**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.126**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
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 944720fdd..beadf3568 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
@@ -5,11 +5,11 @@
Computation times
=================
-**05:07.609** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:27.970**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:21.333**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:41.741**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:18.350**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:09.260**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.955**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**03:34.764** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **01:19.186**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **01:07.420**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **00:40.742**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:09.466**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:09.319**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.630**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
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 a6c11776f..828be64ed 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
@@ -191,7 +191,6 @@ file and apply it.
-
We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.
@@ -222,910 +221,483 @@ 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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
+ 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
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (rc.outer.outer*288)
- let cse_var_2: int32 = (ry.outer.outer*7)
+ 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" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 196), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 197)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 197), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 198)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 146)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 199)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 199), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 392), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 393)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 393), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 394)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 394), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 395)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 395), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 588), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 589)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 589), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 590)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 590), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 591)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 591), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 784), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 785)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 785), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 786)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 786), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 787)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 787), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 980), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 981)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 755)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 982)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 982), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 983)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 983), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1176), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1177)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1177), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1178)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1178), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1179)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 909)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1372), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1373)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1373), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1374)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1374), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1375)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1375), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1568), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1569)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1569), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1570)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1570), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1571)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1571), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1364)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1765)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1765), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1766)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1766), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1767)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1767), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1960), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
+ 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 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1961)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1961), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
+ 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 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1962)] = @tir.if_then_else(((((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1518)], 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 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1963)] = @tir.if_then_else(((((floordiv(floormod(((threadIdx.x_1*4) + 1963), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1963), 9)*7)) + cse_var_2) + 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) + 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)
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 98), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 196), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 245), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 343), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 19), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 490), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 539), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 637), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 686), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 33), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 21), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[192]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[384]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[576]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[193]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[385]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[577]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[194]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[386]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[578]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[195]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[387]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[579]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[4]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[196]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[388]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[580]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[5]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[197]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[389]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[581]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[198]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[390]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[582]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[7]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[199]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[391]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[583]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[8]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[200]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[392]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[584]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[201]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[393]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[585]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[10]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[202]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[394]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[586]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[11]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[203]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[395]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[587]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[204]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[396]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[588]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[13]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[205]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[397]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[589]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[14]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[206]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[398]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[590]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[207]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[399]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[591]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[16]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[208]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[400]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[592]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[17]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[209]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[401]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[593]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[210]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[402]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[594]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[19]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[211]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[403]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[595]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[20]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[212]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[404]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[596]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[213]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[405]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[597]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[22]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[214]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[406]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[598]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[23]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[215]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[407]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[599]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[216]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[408]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[600]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[217]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[409]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[601]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[218]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[410]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[602]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[219]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[411]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[603]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[220]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[412]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[604]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[221]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[413]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[605]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[222]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[414]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[606]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[223]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[415]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[607]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[224]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[416]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[608]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[225]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[417]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[609]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[226]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[418]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[610]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[227]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[419]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[611]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[228]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[420]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[612]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[229]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[421]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[613]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[230]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[422]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[614]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[231]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[423]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[615]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[232]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[424]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[616]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[233]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[425]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[617]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[234]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[426]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[618]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[235]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[427]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[619]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[236]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[428]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[620]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[237]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[429]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[621]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[238]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[430]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[622]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[239]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[431]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[623]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[48]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[240]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[432]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[624]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[49]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[241]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[433]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[625]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[50]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[242]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[434]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[626]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[51]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[243]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[435]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[627]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[52]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[244]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[436]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[628]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[53]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[245]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[437]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[629]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[54]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[246]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[438]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[630]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[55]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[247]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[439]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[631]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[56]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[248]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[440]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[632]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[57]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[249]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[441]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[633]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[58]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[250]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[442]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[634]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[59]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[251]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[443]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[635]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[60]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[252]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[444]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[636]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[61]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[253]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[445]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[637]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[62]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[254]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[446]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[638]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[63]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[255]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[447]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[639]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[64]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[256]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[448]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[640]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[65]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[257]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[449]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[641]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[66]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[258]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[450]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[642]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[67]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[259]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[451]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[643]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[68]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[260]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[452]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[644]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[69]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[261]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[453]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[645]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[70]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[262]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[454]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[646]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[71]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[263]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[455]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[647]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[72]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[264]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[456]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[648]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[73]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[265]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[457]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[649]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[74]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[266]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[458]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[650]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[75]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[267]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[459]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[651]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[76]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[268]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[460]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[652]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[77]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[269]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[461]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[653]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[78]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[270]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[462]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[654]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[79]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[271]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[463]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[655]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[80]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[272]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[464]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[656]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[81]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[273]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[465]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[657]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[82]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[274]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[466]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[658]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[83]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[275]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[467]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[659]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[84]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[276]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[468]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[660]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[85]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[277]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[469]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[661]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[86]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[278]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[470]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[662]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[87]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[279]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[471]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[663]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[88]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[280]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[472]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[664]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[89]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[281]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[473]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[665]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[90]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[282]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[474]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[666]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[91]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[283]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[475]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[667]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[92]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[284]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[476]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[668]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[93]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[285]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[477]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[669]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[94]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[286]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[478]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[670]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[95]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[287]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[479]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[671]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[96]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[288]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[480]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[672]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[97]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[289]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[481]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[673]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[98]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[290]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[482]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[674]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[291]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[483]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[675]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[100]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[292]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[484]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[676]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[101]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[293]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[485]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[677]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[294]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[486]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[678]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[103]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[295]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[487]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[679]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[104]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[296]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[488]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[680]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[297]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[489]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[681]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[106]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[298]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[490]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[682]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[107]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[299]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[491]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[683]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[300]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[492]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[684]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[109]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[301]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[493]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[685]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[110]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[302]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[494]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[686]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[303]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[495]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[687]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[112]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[304]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[496]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[688]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[113]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[305]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[497]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[689]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[306]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[498]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[690]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[115]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[307]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[499]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[691]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[116]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[308]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[500]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[692]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[309]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[501]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[693]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[118]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[310]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[502]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[694]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[119]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[311]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[503]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[695]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[120]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[312]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[504]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[696]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[121]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[313]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[505]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[697]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[122]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[314]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[506]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[698]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[123]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[315]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[507]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[699]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[124]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[316]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[508]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[700]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[125]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[317]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[509]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[701]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[126]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[318]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[510]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[702]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[127]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[319]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[511]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[703]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[128]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[320]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[512]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[704]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[129]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[321]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[513]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[705]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[130]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[322]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[514]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[706]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[131]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[323]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[515]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[707]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[132]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[324]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[516]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[708]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[133]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[325]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[517]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[709]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[134]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[326]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[518]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[710]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[135]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[327]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[519]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[711]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[136]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[328]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[520]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[712]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[137]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[329]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[521]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[713]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[138]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[330]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[522]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[714]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[139]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[331]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[523]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[715]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[140]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[332]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[524]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[716]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[141]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[333]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[525]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[717]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[142]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[334]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[526]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[718]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[143]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[335]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[527]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[719]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[144]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[336]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[528]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[720]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[145]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[337]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[529]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[721]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[146]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[338]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[530]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[722]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[147]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[339]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[531]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[723]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[148]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[340]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[532]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[724]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[149]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[341]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[533]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[725]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[150]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[342]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[534]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[726]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[151]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[343]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[535]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[727]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[152]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[344]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[536]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[728]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[153]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[345]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[537]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[729]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[154]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[346]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[538]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[730]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[155]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[347]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[539]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[731]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[156]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[348]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[540]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[732]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[157]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[349]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[541]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[733]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[158]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[350]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[542]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[734]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[159]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[351]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[543]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[735]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[160]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[352]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[544]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[736]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[161]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[353]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[545]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[737]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[162]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[354]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[546]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[738]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[163]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[355]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[547]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[739]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[164]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[356]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[548]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[740]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[165]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[357]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[549]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[741]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[166]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[358]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[550]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[742]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[167]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[359]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[551]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[743]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[168]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[360]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[552]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[744]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[169]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[361]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[553]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[745]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[170]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[362]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[554]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[746]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[171]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[363]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[555]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[747]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[172]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[364]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[556]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[748]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[173]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[365]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[557]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[749]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[174]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[366]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[558]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[750]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[175]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[367]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[559]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[751]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[176]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[368]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[560]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[752]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[177]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[369]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[561]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[753]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[178]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[370]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[562]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[754]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[179]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[371]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[563]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[755]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[180]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[372]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[564]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[756]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[181]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[373]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[565]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[757]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[182]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[374]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[566]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[758]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[183]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[375]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[567]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[759]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[184]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[376]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[568]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[760]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[185]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[377]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[569]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[761]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[186]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[378]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[570]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[762]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[187]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[379]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[571]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[763]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[188]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[380]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[572]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[764]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[189]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[381]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[573]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[765]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[190]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[382]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[574]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[766]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[191]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[383]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[575]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[767]))
+ 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((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 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((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 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((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 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((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 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((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 832), 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((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1024), 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((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1088), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1216), 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((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1280), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1408), 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((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1472), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1600), 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((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1664), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1792), 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((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1856), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1984), 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((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2048), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2176), 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((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2240), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2368), 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((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2432), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2560), 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((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2624), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2752), 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((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2816), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2944), 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((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 3008), 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) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*8) + i1.inner) + 2)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*8) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 294)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*8) + i1.inner) + 6)]), 0f32)
+ 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)
+ }
}
}
}
@@ -1178,7 +750,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.237 ms
+ Execution time of this operator: 0.360 ms
@@ -1224,34 +796,34 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
- 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=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=64)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
- conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
- compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1271,14 +843,14 @@ 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=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1296,867 +868,430 @@ 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__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[768];
+ 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];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 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;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 196)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 197)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 197) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 198)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 146)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 199)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 199) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 394)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 395)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 395) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 588)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 589)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 590)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 591)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 591) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 786)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 786) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 787)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 787) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 980)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 981)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 755)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 982)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 982) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 983)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 983) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1178) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1179)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 909)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1372)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1373)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1373) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1374)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1374) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1375)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1375) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1570)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1570) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1571)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1571) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1764)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1765)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1765) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1766)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1766) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1767)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1767) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1960)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1961)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
+ 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) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1962)] = (((((ry_outer_outer + (((((int)threadIdx.x) * 4) / 9) + 1)) < 8) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1518)] : 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) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1963)] = (((((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1963) / 9) * 7)) + (ry_outer_outer * 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);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 2) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 4) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 33) {
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 21) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[192]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[384]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[576]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[193]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[385]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[577]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[194]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[386]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[578]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[3]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[195]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[387]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[579]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[4]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[196]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[388]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[580]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[5]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[197]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[389]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[581]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[6]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[198]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[390]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[582]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[7]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[199]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[391]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[583]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[8]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[200]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[392]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[584]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[9]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[201]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[393]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[585]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[10]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[202]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[394]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[586]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[11]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[203]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[395]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[587]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[12]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[204]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[396]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[588]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[13]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[205]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[397]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[589]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[14]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[206]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[398]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[590]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[15]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[207]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[399]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[591]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[16]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[208]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[400]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[592]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[17]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[209]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[401]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[593]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[18]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[210]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[402]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[594]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[19]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[211]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[403]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[595]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[20]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[212]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[404]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[596]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[21]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[213]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[405]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[597]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[22]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[214]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[406]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[598]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[23]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[215]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[407]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[599]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[216]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[408]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[600]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[217]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[409]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[601]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[218]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[410]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[602]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[219]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[411]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[603]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[220]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[412]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[604]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[221]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[413]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[605]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[222]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[414]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[606]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[223]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[415]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[607]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[224]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[416]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[608]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[225]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[417]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[609]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[226]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[418]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[610]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[227]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[419]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[611]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[228]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[420]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[612]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[229]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[421]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[613]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[230]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[422]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[614]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[231]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[423]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[615]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[232]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[424]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[616]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[233]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[425]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[617]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[234]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[426]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[618]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[235]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[427]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[619]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[236]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[428]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[620]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[237]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[429]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[621]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[238]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[430]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[622]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[239]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[431]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[623]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[48]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[240]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[432]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[624]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[49]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[241]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[433]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[625]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[50]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[242]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[434]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[626]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[51]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[243]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[435]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[627]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[52]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[244]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[436]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[628]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[53]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[245]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[437]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[629]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[54]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[246]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[438]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[630]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[55]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[247]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[439]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[631]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[56]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[248]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[440]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[632]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[57]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[249]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[441]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[633]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[58]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[250]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[442]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[634]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[59]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[251]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[443]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[635]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[60]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[252]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[444]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[636]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[61]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[253]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[445]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[637]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[62]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[254]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[446]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[638]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[63]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[255]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[447]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[639]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[64]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[256]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[448]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[640]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[65]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[257]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[449]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[641]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[66]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[258]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[450]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[642]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[67]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[259]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[451]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[643]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[68]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[260]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[452]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[644]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[69]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[261]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[453]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[645]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[70]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[262]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[454]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[646]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[71]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[263]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[455]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[647]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[72]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[264]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[456]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[648]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[73]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[265]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[457]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[649]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[74]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[266]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[458]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[650]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[75]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[267]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[459]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[651]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[76]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[268]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[460]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[652]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[77]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[269]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[461]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[653]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[78]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[270]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[462]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[654]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[79]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[271]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[463]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[655]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[80]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[272]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[464]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[656]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[81]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[273]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[465]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[657]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[82]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[274]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[466]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[658]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[83]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[275]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[467]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[659]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[84]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[276]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[468]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[660]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[85]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[277]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[469]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[661]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[86]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[278]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[470]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[662]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[87]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[279]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[471]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[663]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[88]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[280]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[472]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[664]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[89]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[281]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[473]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[665]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[90]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[282]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[474]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[666]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[91]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[283]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[475]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[667]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[92]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[284]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[476]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[668]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[93]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[285]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[477]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[669]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[94]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[286]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[478]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[670]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[95]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[287]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[479]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[671]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[96]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[288]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[480]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[672]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[97]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[289]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[481]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[673]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[98]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[290]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[482]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[674]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[99]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[291]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[483]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[675]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[100]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[292]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[484]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[676]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[101]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[293]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[485]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[677]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[102]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[294]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[486]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[678]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[103]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[295]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[487]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[679]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[104]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[296]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[488]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[680]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[105]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[297]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[489]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[681]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[106]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[298]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[490]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[682]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[107]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[299]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[491]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[683]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[108]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[300]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[492]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[684]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[109]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[301]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[493]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[685]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[110]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[302]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[494]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[686]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[111]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[303]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[495]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[687]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[112]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[304]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[496]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[688]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[113]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[305]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[497]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[689]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[114]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[306]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[498]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[690]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[115]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[307]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[499]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[691]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[116]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[308]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[500]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[692]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[117]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[309]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[501]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[693]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[118]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[310]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[502]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[694]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[119]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[311]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[503]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[695]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[120]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[312]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[504]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[696]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[121]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[313]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[505]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[697]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[122]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[314]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[506]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[698]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[123]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[315]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[507]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[699]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[124]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[316]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[508]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[700]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[125]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[317]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[509]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[701]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[126]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[318]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[510]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[702]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[127]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[319]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[511]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[703]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[128]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[320]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[512]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[704]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[129]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[321]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[513]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[705]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[130]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[322]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[514]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[706]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[131]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[323]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[515]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[707]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[132]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[324]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[516]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[708]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[133]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[325]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[517]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[709]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[134]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[326]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[518]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[710]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[135]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[327]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[519]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[711]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[136]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[328]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[520]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[712]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[137]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[329]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[521]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[713]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[138]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[330]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[522]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[714]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[139]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[331]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[523]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[715]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[140]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[332]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[524]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[716]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[141]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[333]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[525]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[717]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[142]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[334]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[526]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[718]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[143]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[335]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[527]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[719]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[144]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[336]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[528]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[720]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[145]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[337]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[529]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[721]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[146]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[338]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[530]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[722]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[147]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[339]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[531]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[723]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[148]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[340]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[532]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[724]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[149]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[341]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[533]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[725]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[150]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[342]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[534]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[726]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[151]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[343]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[535]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[727]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[152]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[344]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[536]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[728]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[153]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[345]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[537]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[729]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[154]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[346]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[538]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[730]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[155]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[347]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[539]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[731]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[156]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[348]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[540]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[732]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[157]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[349]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[541]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[733]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[158]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[350]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[542]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[734]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[159]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[351]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[543]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[735]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[160]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[352]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[544]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[736]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[161]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[353]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[545]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[737]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[162]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[354]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[546]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[738]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[163]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[355]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[547]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[739]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[164]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[356]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[548]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[740]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[165]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[357]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[549]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[741]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[166]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[358]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[550]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[742]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[167]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[359]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[551]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[743]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[168]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[360]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[552]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[744]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[169]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[361]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[553]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[745]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[170]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[362]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[554]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[746]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[171]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[363]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[555]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[747]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[172]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[364]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[556]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[748]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[173]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[365]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[557]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[749]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[174]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[366]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[558]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[750]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[175]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[367]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[559]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[751]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[176]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[368]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[560]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[752]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[177]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[369]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[561]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[753]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[178]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[370]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[562]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[754]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[179]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[371]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[563]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[755]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[180]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[372]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[564]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[756]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[181]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[373]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[565]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[757]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[182]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[374]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[566]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[758]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[183]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[375]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[567]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[759]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[184]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[376]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[568]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[760]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[185]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[377]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[569]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[761]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[186]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[378]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[570]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[762]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[187]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[379]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[571]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[763]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[188]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[380]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[572]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[764]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[189]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[381]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[573]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[765]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[190]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[382]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[574]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[766]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[191]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[383]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[575]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[767]));
+ 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) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 2)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 6)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
@@ -2215,7 +1350,7 @@ 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 27.970 seconds)
+ **Total running time of the script:** ( 1 minutes 7.420 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 200979e79..8839ea7bf 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
@@ -616,7 +616,7 @@ 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)
- 9.7115 9.7256 9.7285 9.6803 0.0221
+ 9.8776 9.8787 9.8992 9.8548 0.0181
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 3fe3a2e5a..b2f279d9e 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
@@ -635,7 +635,7 @@ 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)
- 781.7172 781.8939 782.0381 781.2196 0.3568
+ 754.5500 757.0768 758.6450 747.9284 4.7258
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.333 seconds)
+ **Total running time of the script:** ( 1 minutes 19.186 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 36e987ce8..284b75f68 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
@@ -330,7 +330,6 @@ file and apply it.
-
We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
layout transformation, parallelization, vectorization, unrolling, and operator fusion.
@@ -362,77 +361,28 @@ 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.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_17: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_16: int32 = (cse_var_17 + 1)
- let cse_var_15: int32 = (cse_var_17 + 11)
- let cse_var_14: int32 = (cse_var_17 + 12)
- let cse_var_13: int32 = (cse_var_17 + 13)
- let cse_var_12: int32 = (cse_var_17 + 14)
- let cse_var_11: int32 = (cse_var_17 + 15)
- let cse_var_10: int32 = (cse_var_17 + 2)
- let cse_var_9: int32 = (cse_var_17 + 3)
- let cse_var_8: int32 = (cse_var_17 + 4)
- let cse_var_7: int32 = (cse_var_17 + 5)
- let cse_var_6: int32 = (cse_var_17 + 6)
- let cse_var_5: int32 = (cse_var_17 + 7)
- let cse_var_4: int32 = (cse_var_17 + 8)
- let cse_var_3: int32 = (cse_var_17 + 9)
- let cse_var_2: int32 = (cse_var_17 + 10)
- {
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
- compute[cse_var_20] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_20]), 0f32)
- }
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -486,7 +436,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.844 ms
+ Execution time of this operator: 1.533 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 c9f363cee..ed72b4ace 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.088** total execution time for **how_to_tune_with_autotvm** files:
+**00:46.558** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.137**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.249**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.235**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.234**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.232**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:45.737**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.208**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.196**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:00.195**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
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 886ec0c14..c7a354e42 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
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 101.91/101.91 result: MeasureResult(costs=(0.002271515416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6228275299072266, timestamp=1653702966.3588765) [('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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.26/42.26 result: MeasureResult(costs=(0.005478168421052631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8430910110473633, timestamp=1653702431.0350013) [('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: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.26 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
@@ -1247,7 +1247,7 @@ 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9c664cdfa2
+ 12: 0x00007f2c7323bfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ 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: 144.25/144.25 result: MeasureResult(costs=(0.00160487599,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4451184272766113, timestamp=1653702992.3415928) [('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: 143.81/143.81 result: MeasureResult(costs=(0.00160972107,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3969709873199463, timestamp=1653702450.6702278) [('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
@@ -2437,7 +2437,7 @@ 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
- Time cost of this operator: 0.002033
+ Time cost of this operator: 0.002015
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 56a566f54..33640a07e 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
@@ -294,10 +294,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.0 98.744 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.079 0.971 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.284 (1, 1, 10, 10, 3) 1 1
- Total_time - 316.981 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.755 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.955 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.911 0.29 (1, 1, 10, 10, 3) 1 1
+ Total_time - 314.211 - - - -
@@ -359,10 +359,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 228.8 98.795 (1, 1, 10, 10, 6) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.967 0.849 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.823 0.355 (1, 3, 10, 10, 1) 1 1
- Total_time - 231.59 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 194.3 98.729 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 0.865 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.407 (1, 3, 10, 10, 1) 1 1
+ Total_time - 196.802 - - - -
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 313fdbf53..70ad0fc10 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
@@ -5,10 +5,10 @@
Computation times
=================
-**00:48.727** total execution time for **how_to_work_with_microtvm** files:
+**00:46.418** total execution time for **how_to_work_with_microtvm** files:
-- **00:44.241**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.829**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.227**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.217**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.213**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:42.338**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.529**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.192**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.182**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.177**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
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 3b52b4aef..2799c43f8 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
@@ -5,8 +5,8 @@
Computation times
=================
-**00:12.578** total execution time for **how_to_work_with_relay** files:
+**00:05.292** total execution time for **how_to_work_with_relay** files:
-- **00:10.426**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.919**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.233**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:03.670**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.411**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.211**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
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 7c64fd5c1..c726fd3f3 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
@@ -5,13 +5,13 @@
Computation times
=================
-**00:06.167** total execution time for **how_to_work_with_schedules** files:
+**00:05.311** total execution time for **how_to_work_with_schedules** files:
-- **00:02.217**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.276**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.767**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.762**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.333**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.311**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.257**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.244**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.043**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:00.875**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.701**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.692**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.300**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.243**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.233**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.225**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
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 451cbf1a5..8d4677b46 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ 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/tmp2f8oh8hc/input0.cc'\nsource_filename = \"/tmp/tmp2f8oh8hc/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/tmpxqu7735t/input0.cc'\nsource_filename = \"/tmp/tmpxqu7735t/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 412a8741d..691cd9ef3 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:21.896** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.756** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:21.673**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.224**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.546**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.210**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
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 566504da8..c01aa0098 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -267,7 +267,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 23.25s!
+ resnet18_v1 inference graph built in 20.96s!
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 20f8d7868..612c18593 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -303,7 +303,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.96s!
+ yolov3-tiny inference graph built in 14.87s!
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 e1178d22f..5e2ae558d 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
@@ -5,7 +5,7 @@
Computation times
=================
-**01:31.625** total execution time for **topic_vta_tutorials_frontend** files:
+**01:27.568** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:48.077**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:43.548**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.713**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:40.855**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
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 5e39944b2..e8a71345e 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
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.631** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.556** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.033**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.598**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.997**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.558**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
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 d3b6e83b8..756636b21 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.075** total execution time for **topic_vta_tutorials** files:
+**00:00.997** total execution time for **topic_vta_tutorials** files:
-- **00:00.548**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.527**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.504**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.493**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index f30677692..22b3087c9 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -188,7 +188,6 @@ trials, we can load the best schedule from the log file and apply it.
-
Inspecting the Optimized Schedule
---------------------------------
We can lower the schedule to see the IR after auto-scheduling. The
@@ -306,7 +305,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 95.336 ms
+ Execution time of this operator: 92.877 ms
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index aaee01b6f..f81e9f085 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 499.1216036099968, 'median': 498.5858417499969, 'std': 1.4765700587167203}
+ {'mean': 494.2016846453771, 'median': 494.2348497454077, 'std': 0.5159580382949471}
@@ -494,31 +494,29 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.32/ 17.32 GFLOPS | Progress: (4/20) | 6.22 s
[Task 1/25] Current/Best: 6.16/ 17.32 GFLOPS | Progress: (8/20) | 9.13 s
[Task 1/25] Current/Best: 11.50/ 22.74 GFLOPS | Progress: (12/20) | 11.62 s
[Task 1/25] Current/Best: 16.67/ 22.74 GFLOPS | Progress: (16/20) | 13.32 s
[Task 1/25] Current/Best: 11.59/ 23.84 GFLOPS | Progress: (20/20) | 15.06 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 11.98/ 13.11 GFLOPS | Progress: (4/20) | 3.67 s
[Task 2/25] Current/Best: 14.29/ 18.35 GFLOPS | Progress: (8/20) | 4.99 s
[Task 2/25] Current/Best: 21.01/ 21.01 GFLOPS | Progress: (12/20) | 6.35 s
[Task 2/25] Current/Best: 12.51/ 21.01 GFLOPS | Progress: (16/20) | 7.62 s
[Task 2/25] Current/Best: 19.48/ 21.01 GFLOPS | Progress: (20/20) | 9.22 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.62/ 10.53 GFLOPS | Progress: (4/20) | 5.88 s
[Task 3/25] Current/Best: 15.27/ 16.80 GFLOPS | Progress: (8/20) | 7.83 s
[Task 3/25] Current/Best: 14.82/ 16.80 GFLOPS | Progress: (12/20) | 9.56 s
[Task 3/25] Current/Best: 7.17/ 23.24 GFLOPS | Progress: (16/20) | 11.49 s
[Task 3/25] Current/Best: 12.56/ 23.24 GFLOPS | Progress: (20/20) | 16.01 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.42/ 19.99 GFLOPS | Progress: (4/20) | 2.36 s
[Task 4/25] Current/Best: 6.84/ 19.99 GFLOPS | Progress: (8/20) | 6.78 s
[Task 4/25] Current/Best: 21.75/ 21.75 GFLOPS | Progress: (12/20) | 11.41 s
[Task 4/25] Current/Best: 17.18/ 21.75 GFLOPS | Progress: (16/20) | 13.68 s
[Task 4/25] Current/Best: 13.06/ 21.75 GFLOPS | Progress: (20/20) | 15.74 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.51/ 10.07 GFLOPS | Progress: (4/20) | 2.57 s
[Task 5/25] Current/Best: 11.56/ 12.77 GFLOPS | Progress: (8/20) | 4.65 s
[Task 5/25] Current/Best: 9.96/ 17.92 GFLOPS | Progress: (12/20) | 7.64 s
[Task 5/25] Current/Best: 11.65/ 22.74 GFLOPS | Progress: (16/20) | 9.06 s
[Task 5/25] Current/Best: 11.85/ 22.74 GFLOPS | Progress: (20/20) | 10.96 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.24/ 20.65 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 18.84/ 20.65 GFLOPS | Progress: (8/20) | 5.76 s
[Task 6/25] Current/Best: 12.89/ 20.65 GFLOPS | Progress: (12/20) | 7.70 s
[Task 6/25] Current/Best: 19.68/ 20.65 GFLOPS | Progress: (16/20) | 9.96 s
[Task 6/25] Current/Best: 3.72/ 20.65 GFLOPS | Progress: (20/20) | 12.49 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.74/ 12.15 GFLOPS | Progress: (4/20) | 3.66 s
[Task 7/25] Current/Best: 20.06/ 20.96 GFLOPS | Progress: (8/20) | 5.18 s
[Task 7/25] Current/Best: 15.84/ 20.96 GFLOPS | Progress: (12/20) | 7.11 s
[Task 7/25] Current/Best: 12.22/ 20.96 GFLOPS | Progress: (16/20) | 9.15 s
[Task 7/25] Current/Best: 6.33/ 21.32 GFLOPS | Progress: (20/20) | 11.63 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.99/ 13.99 GFLOPS | Progress: (4/20) | 2.92 s
[Task 8/25] Current/Best: 9.42/ 13.99 GFLOPS | Progress: (8/20) | 7.85 s
[Task 8/25] Current/Best: 12.90/ 13.99 GFLOPS | Progress: (12/20) | 14.09 s
[Task 8/25] Current/Best: 19.11/ 19.11 GFLOPS | Progress: (16/20) | 16.20 s
[Task 8/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 22.81 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.65 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 23.33/ 23.33 GFLOPS | Progress: (8/20) | 13.71 s
[Task 9/25] Current/Best: 8.33/ 23.33 GFLOPS | Progress: (12/20) | 16.11 s
[Task 9/25] Current/Best: 17.56/ 23.33 GFLOPS | Progress: (16/20) | 18.82 s
[Task 9/25] Current/Best: 8.99/ 23.33 GFLOPS | Progress: (20/20) | 26.65 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.33/ 18.33 GFLOPS | Progress: (4/20) | 2.56 s
[Task 10/25] Current/Best: 15.71/ 18.33 GFLOPS | Progress: (8/20) | 4.17 s
[Task 10/25] Current/Best: 12.79/ 18.95 GFLOPS | Progress: (12/20) | 5.70 s
[Task 10/25] Current/Best: 19.08/ 20.46 GFLOPS | Progress: (16/20) | 6.81 s
[Task 10/25] Current/Best: 8.96/ 20.46 GFLOPS | Progress: (20/20
) | 8.37 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.36/ 18.37 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.91/ 18.37 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.10/ 18.37 GFLOPS | Progress: (12/20) | 8.18 s
[Task 11/25] Current/Best: 12.89/ 21.08 GFLOPS | Progress: (16/20) | 11.00 s Done.
-
[Task 11/25] Current/Best: 19.45/ 21.51 GFLOPS | Progress: (20/20) | 13.07 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/ 18.25 GFLOPS | Progress: (4/20) | 5.49 s
[Task 12/25] Current/Best: 5.18/ 18.25 GFLOPS | Progress: (8/20) | 9.25 s
[Task 12/25] Current/Best: 19.14/ 19.14 GFLOPS | Progress: (12/20) | 11.24 s
[Task 12/25] Current/Best: 13.74/ 19.14 GFLOPS | Progress: (16/20) | 14.12 s
[Task 12/25] Current/Best: 15.16/ 19.14 GFLOPS | Progress: (20/20) | 16.07 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.87/ 17.28 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 15.58/ 20.79 GFLOPS | Progress: (8/20) | 6.14 s
[Task 13/25] Current/Best: 19.30/ 21.11 GFLOPS | Progress: (12/20) | 9.07 s
[Task 13/25] Current/Best: 12.19/ 21.11 GFLOPS | Progress: (16/20) | 12.50 s
[Task 13/25] Current/Best: 18.43/ 21.11 GFLOPS | Progress: (20/20) | 14.72 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.61/ 13.61 GFLOPS | Progress: (4/20) | 3.40 s
[Task 14/25] Current/Best: 6.09/ 13.61 GFLOPS | Progress: (8/20) | 5.57 s
[Task 14/25] Current/Best: 20.12/ 20.12 GFLOPS | Progress: (12/20) | 8.12 s
[Task 14/25] Current/Best: 16.10/ 20.12 GFLOPS | Progress: (16/20) | 10.01 s
[Task 14/25] Current/Best: 17.15/ 20.12 GFLOPS | Progress: (20/20) | 11.82 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.06/ 17.44 GFLOPS | Progress: (4/20) | 2.68 s
[Task 15/25] Current/Best: 14.29/ 17.77 GFLOPS | Progress: (8/20) | 4.20 s
[Task 15/25] Current/Best: 10.35/ 22.09 GFLOPS | Progress: (12/20) | 6.33 s
[Task 15/25] Current/Best: 20.11/ 22.09 GFLOPS | Progress: (16/20) | 9.34 s
[Task 15/25] Current/Best: 9.65/ 22.09 GFLOPS | Progress: (20/20) |
10.51 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
- Done.
-
[Task 16/25] Current/Best: 20.21/ 20.21 GFLOPS | Progress: (4/20) | 2.96 s
[Task 16/25] Current/Best: 2.97/ 20.21 GFLOPS | Progress: (8/20) | 4.60 s
[Task 16/25] Current/Best: 19.30/ 20.21 GFLOPS | Progress: (12/20) | 5.84 s
[Task 16/25] Current/Best: 17.55/ 20.21 GFLOPS | Progress: (16/20) | 7.22 s
[Task 16/25] Current/Best: 9.92/ 22.10 GFLOPS | Progress: (20/20) | 9.31 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.13/ 18.71 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.38/ 22.94 GFLOPS | Progress: (8/20) | 7.53 s
[Task 17/25] Current/Best: 16.80/ 22.94 GFLOPS | Progress: (12/20) | 9.61 s
[Task 17/25] Current/Best: 16.44/ 22.94 GFLOPS | Progress: (16/20) | 11.79 s
[Task 17/25] Current/Best: 10.00/ 22.94 GFLOPS | Progress: (20/20) | 13.93 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.37/ 18.12 GFLOPS | Progress: (4/20) | 3.71 s
[Task 18/25] Current/Best: 10.56/ 18.12 GFLOPS | Progress: (8/20) | 7.26 s
[Task 18/25] Current/Best: 19.05/ 19.05 GFLOPS | Progress: (12/20) | 9.20 s
[Task 18/25] Current/Best: 9.94/ 19.05 GFLOPS | Progress: (16/20) | 12.83 s
[Task 18/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (20/20) | 14.35 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 5.96/ 20.15 GFLOPS | Progress: (4/20) | 6.24 s
[Task 19/25] Current/Best: 2.61/ 20.15 GFLOPS | Progress: (8/20) | 9.54 s
[Task 19/25] Current/Best: 19.07/ 20.15 GFLOPS | Progress: (12/20) | 12.38 s
[Task 19/25] Current/Best: 15.01/ 20.15 GFLOPS | Progress: (16/20) | 15.28 s
[Task 19/25] Current/Best: 2.69/ 22.90 GFLOPS | Progress: (20/20) | 18.09 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/ 14.86 GFLOPS | Progress: (4/20) | 3.37 s
[Task 20/25] Current/Best: 10.22/ 14.86 GFLOPS | Progress: (8/20) | 6.91 s
[Task 20/25] Current/Best: 2.32/ 16.46 GFLOPS | Progress: (12/20) | 10.85 s
[Task 20/25] Current/Best: 12.47/ 16.46 GFLOPS | Progress: (16/20) | 14.66 s
[Task 20/25] Current/Best: 13.09/ 21.63 GFLOPS | Progress: (20/20) | 16.75 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.37/ 17.49 GFLOPS | Progress: (4/20) | 3.24 s
[Task 21/25] Current/Best: 14.47/ 17.49 GFLOPS | Progress: (8/20) | 4.84 s
[Task 21/25] Current/Best: 1.61/ 17.49 GFLOPS | Progress: (12/20) | 6.97 s
[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (16/20) | 10.43 s
[Task 21/25] Current/Best: 4.46/ 18.14 GFLOPS | Progress: (20/20)
| 17.79 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20) | 2.65 s Done.
- Done.
-
[Task 22/25] Current/Best: 8.90/ 21.34 GFLOPS | Progress: (8/20) | 4.71 s
[Task 22/25] Current/Best: 19.65/ 21.34 GFLOPS | Progress: (12/20) | 7.04 s
[Task 22/25] Current/Best: 15.10/ 21.34 GFLOPS | Progress: (16/20) | 9.09 s
[Task 22/25] Current/Best: 14.90/ 21.34 GFLOPS | Progress: (20/20) | 10.84 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.24/ 20.12 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 15.71/ 20.12 GFLOPS | Progress: (8/20) | 6.64 s
[Task 23/25] Current/Best: 20.56/ 21.27 GFLOPS | Progress: (12/20) | 8.47 s
[Task 23/25] Current/Best: 5.61/ 21.27 GFLOPS | Progress: (16/20) | 15.77 s
[Task 23/25] Current/Best: 7.41/ 21.27 GFLOPS | Progress: (20/20) | 20.05 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.44/ 8.44 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 1.88/ 8.44 GFLOPS | Progress: (8/20) | 22.82 s
[Task 24/25] Current/Best: 3.97/ 8.44 GFLOPS | Progress: (12/20) | 34.37 s
[Task 24/25] Current/Best: 6.43/ 8.67 GFLOPS | Progress: (16/20) | 40.03 s
[Task 24/25] Current/Best: 3.21/ 8.67 GFLOPS | Progress: (20/20) | 46.15 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
-
[Task 25/25] Current/Best: 1.53/ 2.79 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 5.16/ 7.47 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 5.50/ 7.47 GFLOPS | Progress: (12/20) | 34.39 s
[Task 25/25] Current/Best: 5.60/ 8.47 GFLOPS | Progress: (16/20) | 36.16 s
[Task 25/25] Current/Best: 2.74/ 8.47 GFLOPS | Progress: (20/20) | 46.86 s
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 16.61/ 22.80 GFLOPS | Progress: (16/20) | 13.20 s
[Task 1/25] Current/Best: 11.65/ 23.67 GFLOPS | Progress: (20/20) | 15.86 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 13.17/ 21.39 GFLOPS | Progress: (16/20) | 9.04 s
[Task 2/25] Current/Best: 20.08/ 21.39 GFLOPS | Progress: (20/20) | 10.51 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 7.22/ 23.86 GFLOPS | Progress: (16/20) | 10.54 s
[Task 3/25] Current/Best: 12.73/ 23.86 GFLOPS | Progress: (20/20) | 14.95 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 17.51/ 22.14 GFLOPS | Progress: (16/20) | 8.89 s
[Task 4/25] Current/Best: 13.59/ 22.14 GFLOPS | Progress: (20/20) | 10.72 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 11.74/ 23.01 GFLOPS | Progress: (16/20) | 7.78 s
[Task 5/25] Current/Best: 12.07/ 23.01 GFLOPS | Progress: (20/20) | 9.38 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 20.10/ 20.87 GFLOPS | Progress: (16/20) | 8.44 s
[Task 6/25] Current/Best: 3.76/ 20.87 GFLOPS | Progress: (20/20) | 10.89 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 12.25/ 21.10 GFLOPS | Progress: (16/20) | 8.06 s
[Task 7/25] Current/Best: 6.37/ 21.85 GFLOPS | Progress: (20/20) | 10.42 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 19.00/ 19.00 GFLOPS | Progress: (16/20) | 12.48 s
[Task 8/25] Current/Best: 20.39/ 20.39 GFLOPS | Progress: (20/20) | 18.88 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 17.98/ 23.53 GFLOPS | Progress: (16/20) | 15.08 s
[Task 9/25] Current/Best: 9.05/ 23.53 GFLOPS | Progress: (20/20) | 22.72 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 10/25] Current/Best: 19.19/ 20.53 GFLOPS | Progress: (16/20) | 6.21 s
[Task 10/25] Current/Best: 8.92/ 20.53 GFLOPS | Progress: (20/20) | 7.68 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.78/ 21.30 GFLOPS | Progress: (16/20) | 8.79 s
[Task 11/25] Current/Best: 19.48/ 21.57 GFLOPS | Progress: (20/20) | 10.73 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 15.39/ 19.11 GFLOPS | Progress: (16/20) | 10.20 s
[Task 12/25] Current/Best: 15.22/ 19.11 GFLOPS | Progress: (20/20) | 12.08 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 12.34/ 21.81 GFLOPS | Progress: (16/20) | 8.85 s
[Task 13/25] Current/Best: 18.64/ 21.81 GFLOPS | Progress: (20/20) | 10.95 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 16.83/ 20.13 GFLOPS | Progress: (16/20) | 7.99 s
[Task 14/25] Current/Best: 17.32/ 20.13 GFLOPS | Progress: (20/20) | 9.35 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 15/25] Current/Best: 20.40/ 22.28 GFLOPS | Progress: (16/20) | 6.33 s
[Task 15/25] Current/Best: 9.72/ 22.28 GFLOPS | Progress: (20/20) | 7.44 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 17.84/ 20.55 GFLOPS | Progress: (16/20) | 6.54 s
[Task 16/25] Current/Best: 10.01/ 21.35 GFLOPS | Progress: (20/20) | 8.53 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 16.51/ 22.92 GFLOPS | Progress: (16/20) | 9.37 s
[Task 17/25] Current/Best: 10.06/ 22.92 GFLOPS | Progress: (20/20) | 11.41 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.15/ 19.22 GFLOPS | Progress: (16/20) | 9.45 s
[Task 18/25] Current/Best: 20.87/ 20.87 GFLOPS | Progress: (20/20) | 10.90 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 14.82/ 21.91 GFLOPS | Progress: (16/20) | 11.54 s
[Task 19/25] Current/Best: 2.70/ 23.83 GFLOPS | Progress: (20/20) | 14.21 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 12.43/ 16.72 GFLOPS | Progress: (16/20) | 10.70 s
[Task 20/25] Current/Best: 12.87/ 22.38 GFLOPS | Progress: (20/20) | 12.71 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 21/25] Current/Best: 18.01/ 18.01 GFLOPS | Progress: (16/20) | 7.56 s
[Task 21/25] Current/Best: 4.47/ 18.01 GFLOPS | Progress: (20/20) | 14.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 15.57/ 22.18 GFLOPS | Progress: (16/20) | 7.16 s
[Task 22/25] Current/Best: 14.24/ 22.18 GFLOPS | Progress: (20/20) | 8.74 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 6.38/ 21.63 GFLOPS | Progress: (16/20) | 13.37 s
[Task 23/25] Current/Best: 7.86/ 21.63 GFLOPS | Progress: (20/20) | 17.46 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 6.15/ 9.05 GFLOPS | Progress: (16/20) | 13.75 s
[Task 24/25] Current/Best: 3.42/ 9.05 GFLOPS | Progress: (20/20) | 19.58 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 25/25] Current/Best: 5.86/ 8.71 GFLOPS | Progress: (16/20) | 13.58 s
[Task 25/25] Current/Best: 2.83/ 8.71 GFLOPS | Progress: (20/20) | 24.24 s
The output from this tuning process will look something like this:
@@ -660,8 +658,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.7100475100019, 'median': 417.276789050004, 'std': 1.0356913707730897}
- unoptimized: {'mean': 499.1216036099968, 'median': 498.5858417499969, 'std': 1.4765700587167203}
+ optimized: {'mean': 415.04260934423655, 'median': 413.9633630635217, 'std': 3.0879960792901824}
+ unoptimized: {'mean': 494.2016846453771, 'median': 494.2348497454077, 'std': 0.5159580382949471}
@@ -681,7 +679,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 23.329 seconds)
+ **Total running time of the script:** ( 8 minutes 34.913 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 5eaefa56c..6294e6d0a 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.363e-07 secs/op
+ 1.308e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 0fd39d8f9..1f01de0ff 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x214b95e0)), stage(b, placeholder(b, 0x213cd030)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x1aadaeb0)), stage(b, placeholder(b, 0x22dd0a40)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index acdcb63f7..8e1f820c1 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**13:10.692** total execution time for **tutorial** files:
+**11:10.413** total execution time for **tutorial** files:
-- **10:23.329**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:04.141**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:49.661**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:27.050**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.913**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.399**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.749**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.237**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.053**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.052**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **08:34.913**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:01.997**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:40.350**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:25.865**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:25.683**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:00.701**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.544**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.207**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.041**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.039**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.038**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.036**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 8dfc37c80..7fc907c88 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -344,7 +344,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000006
+ parallel: 0.000008
@@ -397,7 +397,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000025
+ vector: 0.000024
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.754150001346716e-06 1.0
- naive 5.9583999999999996e-06 0.7684143328366312
- parallel 6.1857e-06 0.7977276682712725
- vector 2.46431e-05 3.1780530420123507
+ numpy 7.977667264640331e-06 1.0
+ naive 5.8364e-06 0.7315923071734092
+ parallel 7.8711e-06 0.9866418012803476
+ vector 2.4443499999999997e-05 3.063990912273529
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019514
+ Numpy running time: 0.018742
@@ -897,7 +897,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: 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: 3.585101
+ none: 3.499623
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.331006
+ blocking: 0.299359
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.345611
+ vectorization: 0.332607
@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], []),
@@ -1160,7 +1160,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.142390
+ loop permutation: 0.116393
@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], []),
@@ -1257,7 +1257,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.114451
+ array packing: 0.109518
@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], []),
@@ -1348,7 +1348,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.114477
+ block caching: 0.110842
@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], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.147660
+ parallelization: 0.144892
@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], []),
@@ -1511,13 +1511,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.5851011227000003 1.0
- blocking 0.3310062404 0.09232828561073156
- vectorization 0.3456109804 0.09640201728527939
- loop permutation 0.1423903215 0.0397172399401564
- array packing 0.11445063439999999 0.031923962667419904
- block caching 0.114477286 0.03193139665577556
- parallelization 0.1476596818 0.04118703399049313
+ none 3.4996227185000004 1.0
+ blocking 0.2993590649 0.08554038220105925
+ vectorization 0.33260651069999997 0.09504067651114145
+ loop permutation 0.11639349769999999 0.033258870187552185
+ array packing 0.10951779670000002 0.0312941724035159
+ block caching 0.1108422341 0.03167262388429943
+ parallelization 0.14489193620000002 0.04140215899104211
@@ -1554,7 +1554,7 @@ the computation for specific platforms.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.141 seconds)
+ **Total running time of the script:** ( 1 minutes 1.997 seconds)
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 721d2c5d3..c939f0ff6 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-2389f1f0d82bfc78e5fb4464423326478b685aed
+2b0e082f39b408f750a9c6f6181a75e8a2e7a0e2
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 17ebbfd39..0393062e4 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipd71e3628-38c2-4d5a-8075-c0f944682a3a from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipcaa497d7-ca8d-4f0a-8874-38be19d8c70d 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 e30bf234e..a00455895 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,50 +406,41 @@ 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]
- 0%| | 16.0k/41.5M [00:00<07:34, 95.7kB/s]
- 0%| | 40.0k/41.5M [00:00<05:52, 123kB/s]
- 0%| | 88.0k/41.5M [00:00<03:39, 198kB/s]
- 0%| | 184k/41.5M [00:00<02:05, 345kB/s]
- 1%| | 360k/41.5M [00:00<01:12, 598kB/s]
- 2%|1 | 728k/41.5M [00:01<00:37, 1.14MB/s]
- 3%|3 | 1.42M/41.5M [00:01<00:19, 2.18MB/s]
- 7%|6 | 2.77M/41.5M [00:01<00:08, 4.53MB/s]
- 9%|9 | 3.91M/41.5M [00:01<00:06, 6.23MB/s]
- 11%|#1 | 4.62M/41.5M [00:01<00:06, 5.61MB/s]
- 14%|#3 | 5.77M/41.5M [00:01<00:05, 6.77MB/s]
- 17%|#6 | 6.98M/41.5M [00:01<00:04, 7.66MB/s]
- 20%|## | 8.35M/41.5M [00:01<00:03, 9.28MB/s]
- 22%|##2 | 9.32M/41.5M [00:02<00:04, 8.07MB/s]
- 25%|##4 | 10.2M/41.5M [00:02<00:04, 7.94MB/s]
- 27%|##7 | 11.3M/41.5M [00:02<00:03, 8.40MB/s]
- 31%|### | 12.8M/41.5M [00:02<00:03, 10.0MB/s]
- 33%|###3 | 13.8M/41.5M [00:02<00:03, 8.61MB/s]
- 35%|###5 | 14.7M/41.5M [00:02<00:03, 8.23MB/s]
- 38%|###7 | 15.7M/41.5M [00:02<00:03, 8.54MB/s]
- 41%|####1 | 17.0M/41.5M [00:02<00:02, 9.81MB/s]
- 43%|####3 | 18.0M/41.5M [00:03<00:02, 8.48MB/s]
- 46%|####5 | 19.0M/41.5M [00:03<00:02, 8.41MB/s]
- 49%|####8 | 20.1M/41.5M [00:03<00:02, 8.74MB/s]
- 52%|#####1 | 21.5M/41.5M [00:03<00:02, 9.94MB/s]
- 54%|#####4 | 22.4M/41.5M [00:03<00:02, 8.57MB/s]
- 56%|#####6 | 23.4M/41.5M [00:03<00:02, 8.45MB/s]
- 59%|#####9 | 24.6M/41.5M [00:03<00:01, 9.04MB/s]
- 61%|######1 | 25.5M/41.5M [00:04<00:01, 8.94MB/s]
- 63%|######3 | 26.3M/41.5M [00:04<00:01, 8.40MB/s]
- 66%|######6 | 27.5M/41.5M [00:04<00:01, 8.91MB/s]
- 69%|######9 | 28.8M/41.5M [00:04<00:01, 10.2MB/s]
- 72%|#######1 | 29.8M/41.5M [00:04<00:01, 8.67MB/s]
- 74%|#######4 | 30.7M/41.5M [00:04<00:01, 8.50MB/s]
- 77%|#######6 | 31.9M/41.5M [00:04<00:01, 8.82MB/s]
- 80%|######## | 33.2M/41.5M [00:04<00:00, 10.0MB/s]
- 82%|########2 | 34.2M/41.5M [00:05<00:00, 8.62MB/s]
- 85%|########4 | 35.1M/41.5M [00:05<00:00, 8.44MB/s]
- 88%|########7 | 36.3M/41.5M [00:05<00:00, 8.81MB/s]
- 90%|######### | 37.5M/41.5M [00:05<00:00, 9.63MB/s]
- 93%|#########2| 38.4M/41.5M [00:05<00:00, 8.28MB/s]
- 95%|#########5| 39.5M/41.5M [00:05<00:00, 8.65MB/s]
- 98%|#########8| 40.7M/41.5M [00:05<00:00, 8.96MB/s]
-100%|##########| 41.5M/41.5M [00:05<00:00, 7.38MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:48, 92.8kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:55, 147kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:30, 207kB/s]
+ 0%| | 192k/41.5M [00:00<02:05, 344kB/s]
+ 1%| | 392k/41.5M [00:00<01:07, 637kB/s]
+ 2%|1 | 784k/41.5M [00:01<00:35, 1.19MB/s]
+ 4%|3 | 1.54M/41.5M [00:01<00:18, 2.30MB/s]
+ 7%|7 | 3.00M/41.5M [00:01<00:09, 4.31MB/s]
+ 11%|# | 4.47M/41.5M [00:01<00:06, 5.68MB/s]
+ 14%|#4 | 5.94M/41.5M [00:01<00:05, 6.61MB/s]
+ 18%|#7 | 7.41M/41.5M [00:01<00:04, 7.24MB/s]
+ 21%|##1 | 8.88M/41.5M [00:02<00:04, 7.68MB/s]
+ 25%|##4 | 10.3M/41.5M [00:02<00:04, 7.98MB/s]
+ 28%|##8 | 11.8M/41.5M [00:02<00:03, 8.20MB/s]
+ 32%|###2 | 13.3M/41.5M [00:02<00:03, 8.34MB/s]
+ 36%|###5 | 14.8M/41.5M [00:02<00:03, 8.44MB/s]
+ 39%|###9 | 16.2M/41.5M [00:03<00:03, 8.51MB/s]
+ 43%|####2 | 17.7M/41.5M [00:03<00:02, 8.56MB/s]
+ 46%|####6 | 19.2M/41.5M [00:03<00:02, 8.60MB/s]
+ 50%|####9 | 20.6M/41.5M [00:03<00:02, 8.62MB/s]
+ 53%|#####3 | 22.1M/41.5M [00:03<00:02, 8.63MB/s]
+ 57%|#####6 | 23.6M/41.5M [00:03<00:02, 8.64MB/s]
+ 60%|###### | 25.0M/41.5M [00:04<00:01, 8.65MB/s]
+ 64%|######3 | 26.5M/41.5M [00:04<00:01, 8.66MB/s]
+ 67%|######7 | 28.0M/41.5M [00:04<00:01, 8.67MB/s]
+ 71%|####### | 29.4M/41.5M [00:04<00:01, 8.67MB/s]
+ 74%|#######4 | 30.9M/41.5M [00:04<00:01, 8.67MB/s]
+ 78%|#######8 | 32.4M/41.5M [00:04<00:01, 8.68MB/s]
+ 82%|########1 | 33.8M/41.5M [00:05<00:00, 8.68MB/s]
+ 85%|########5 | 35.3M/41.5M [00:05<00:00, 8.67MB/s]
+ 89%|########8 | 36.8M/41.5M [00:05<00:00, 8.66MB/s]
+ 92%|#########2| 38.2M/41.5M [00:05<00:00, 8.67MB/s]
+ 96%|#########5| 39.7M/41.5M [00:05<00:00, 8.67MB/s]
+ 99%|#########9| 41.2M/41.5M [00:06<00:00, 8.67MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 7.21MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index db381bb85..2a8b2b02b 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.631 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.233 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.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_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index c3a111c12..52cee7d76 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,9 +387,10 @@ 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]
- 42%|####2 | 18.8M/44.7M [00:00<00:00, 197MB/s]
- 96%|#########6| 42.9M/44.7M [00:00<00:00, 230MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 226MB/s]
+ 10%|9 | 4.42M/44.7M [00:00<00:00, 46.3MB/s]
+ 20%|#9 | 8.84M/44.7M [00:00<00:00, 43.2MB/s]
+ 75%|#######5 | 33.5M/44.7M [00:00<00:00, 138MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 132MB/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 d3c4dabcb..295127083 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,6 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.823 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download 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 09fa5e8b7..ec18ee312 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:28.427</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:12.664</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:10.631</strong>: <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></li>
-<li><p><strong>01:02.823</strong>: <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></li>
-<li><p><strong>00:58.914</strong>: <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></li>
-<li><p><strong>00:31.143</strong>: <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></li>
-<li><p><strong>00:24.352</strong>: <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></li>
-<li><p><strong>00:22.475</strong>: <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></li>
-<li><p><strong>00:22.076</strong>: <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></li>
-<li><p><strong>00:19.245</strong>: <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></li>
-<li><p><strong>00:14.158</strong>: <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></li>
-<li><p><strong>00:02.609</strong>: <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></li>
+<li><p><strong>01:05.233</strong>: <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></li>
+<li><p><strong>00:59.222</strong>: <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></li>
+<li><p><strong>00:57.204</strong>: <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></li>
+<li><p><strong>00:30.012</strong>: <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></li>
+<li><p><strong>00:23.849</strong>: <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></li>
+<li><p><strong>00:21.845</strong>: <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></li>
+<li><p><strong>00:20.755</strong>: <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></li>
+<li><p><strong>00:18.831</strong>: <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></li>
+<li><p><strong>00:13.279</strong>: <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></li>
+<li><p><strong>00:02.433</strong>: <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></li>
</ul>
</div>
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 ec58e26c1..d038db88e 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -627,7 +627,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 18.0075 16.6107 27.2934 16.4056 3.2379
+ 16.1771 16.1997 16.3861 15.9035 0.1371
</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 cb6d2b079..a1b6af148 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,16 +409,14 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|2 | 3.84M/170M [00:00<00:04, 40.1MB/s]
- 5%|4 | 7.66M/170M [00:00<00:04, 38.0MB/s]
- 14%|#3 | 23.8M/170M [00:00<00:01, 95.9MB/s]
- 27%|##7 | 46.0M/170M [00:00<00:00, 149MB/s]
- 39%|###9 | 66.3M/170M [00:00<00:00, 172MB/s]
- 53%|#####2 | 89.2M/170M [00:00<00:00, 195MB/s]
- 64%|######3 | 108M/170M [00:00<00:00, 190MB/s]
- 74%|#######4 | 126M/170M [00:00<00:00, 179MB/s]
- 89%|########9 | 151M/170M [00:00<00:00, 204MB/s]
-100%|##########| 170M/170M [00:01<00:00, 176MB/s]
+ 11%|# | 17.9M/170M [00:00<00:00, 187MB/s]
+ 25%|##5 | 43.0M/170M [00:00<00:00, 232MB/s]
+ 40%|#### | 68.0M/170M [00:00<00:00, 245MB/s]
+ 54%|#####3 | 91.4M/170M [00:00<00:00, 227MB/s]
+ 68%|######7 | 115M/170M [00:00<00:00, 234MB/s]
+ 81%|########1 | 138M/170M [00:00<00:00, 228MB/s]
+ 95%|#########5| 162M/170M [00:00<00:00, 235MB/s]
+100%|##########| 170M/170M [00:00<00:00, 233MB/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').
@@ -516,7 +514,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 20.035 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 5.941 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download 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 444c0ae5e..4c1a7d73d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,9 +450,7 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
- 39%|###8 | 5.25M/13.6M [00:00<00:00, 52.1MB/s]
- 80%|#######9 | 10.8M/13.6M [00:00<00:00, 55.4MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 37.0MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 181MB/s]
</pre></div>
</div>
</div>
@@ -546,7 +544,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<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)
- 90.4921 90.4585 91.1791 90.2927 0.1491
+ 90.5256 90.5225 90.8171 90.1770 0.0912
</pre></div>
</div>
<div class="admonition note">
@@ -585,7 +583,7 @@ 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 9.494 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.504 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download 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 5c40e4444..0cae0f3fc 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -545,7 +545,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<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)
- 122.4539 122.4579 123.6657 121.7679 0.3363
+ 116.3068 116.2124 118.1089 115.3573 0.5102
</pre></div>
</div>
<div class="admonition note">
@@ -573,7 +573,7 @@ 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 55.501 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.976 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download 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 856dbbdf4..f0dfe3795 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -482,7 +482,7 @@ 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 17.471 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.851 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download 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 29221464a..d469efcab 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,24 +415,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 2%|2 | 3316/132723 [00:00<00:03, 33158.13KB/s]
- 8%|7 | 10096/132723 [00:00<00:02, 53532.78KB/s]
- 13%|#3 | 17895/132723 [00:00<00:01, 64695.56KB/s]
- 19%|#9 | 25797/132723 [00:00<00:01, 70347.37KB/s]
- 25%|##5 | 33765/132723 [00:00<00:01, 73710.24KB/s]
- 31%|###1 | 41531/132723 [00:00<00:01, 75050.72KB/s]
- 37%|###7 | 49420/132723 [00:00<00:01, 76303.20KB/s]
- 43%|####3 | 57341/132723 [00:00<00:00, 77224.74KB/s]
- 49%|####9 | 65264/132723 [00:00<00:00, 77848.51KB/s]
- 55%|#####5 | 73183/132723 [00:01<00:00, 78256.89KB/s]
- 61%|######1 | 81117/132723 [00:01<00:00, 78584.92KB/s]
- 67%|######7 | 88976/132723 [00:01<00:00, 77487.20KB/s]
- 73%|#######2 | 96729/132723 [00:01<00:00, 77214.03KB/s]
- 79%|#######8 | 104453/132723 [00:01<00:00, 77181.47KB/s]
- 85%|########4 | 112387/132723 [00:01<00:00, 77826.14KB/s]
- 91%|######### | 120303/132723 [00:01<00:00, 78215.01KB/s]
- 97%|#########6| 128245/132723 [00:01<00:00, 78570.42KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75253.32KB/s]
+ 5%|5 | 6979/132723 [00:00<00:01, 69783.08KB/s]
+ 12%|#1 | 15751/132723 [00:00<00:01, 80331.68KB/s]
+ 19%|#8 | 24560/132723 [00:00<00:01, 83869.09KB/s]
+ 25%|##5 | 33449/132723 [00:00<00:01, 85846.76KB/s]
+ 32%|###1 | 42332/132723 [00:00<00:01, 86915.47KB/s]
+ 39%|###8 | 51167/132723 [00:00<00:00, 87402.41KB/s]
+ 45%|####5 | 60029/132723 [00:00<00:00, 87799.72KB/s]
+ 52%|#####1 | 68907/132723 [00:00<00:00, 88110.66KB/s]
+ 59%|#####8 | 77728/132723 [00:00<00:00, 88139.71KB/s]
+ 65%|######5 | 86566/132723 [00:01<00:00, 88211.06KB/s]
+ 72%|#######1 | 95400/132723 [00:01<00:00, 88249.06KB/s]
+ 79%|#######8 | 104275/132723 [00:01<00:00, 88397.94KB/s]
+ 85%|########5 | 113115/132723 [00:01<00:00, 88342.77KB/s]
+ 92%|#########1| 121950/132723 [00:01<00:00, 88062.90KB/s]
+ 99%|#########8| 130760/132723 [00:01<00:00, 88073.14KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 86859.44KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -477,7 +475,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 33.935 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.665 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download 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 695a85411..d1eb46394 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>11:10.303</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:25.191</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:20.035</strong>: <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></li>
-<li><p><strong>02:33.935</strong>: <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></li>
-<li><p><strong>01:55.501</strong>: <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></li>
-<li><p><strong>01:17.471</strong>: <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></li>
-<li><p><strong>01:09.494</strong>: <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></li>
-<li><p><strong>00:30.928</strong>: <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></li>
-<li><p><strong>00:22.728</strong>: <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></li>
-<li><p><strong>00:00.210</strong>: <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></li>
+<li><p><strong>03:05.941</strong>: <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></li>
+<li><p><strong>02:20.665</strong>: <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></li>
+<li><p><strong>01:52.976</strong>: <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></li>
+<li><p><strong>01:08.504</strong>: <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></li>
+<li><p><strong>01:06.851</strong>: <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></li>
+<li><p><strong>00:28.471</strong>: <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></li>
+<li><p><strong>00:21.602</strong>: <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></li>
+<li><p><strong>00:00.181</strong>: <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></li>
</ul>
</div>
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 9467040e2..a25453dbb 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -590,7 +590,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5ab718f8-a58c-460e-b325-6f5afcb9fff5 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.zip4aabba12-aeb3-47cb-830c-381cd2f54efd from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index 9e624721e..fc36602ee 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<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>00:39.897</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.769</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:36.220</strong>: <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></li>
-<li><p><strong>00:02.350</strong>: <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></li>
-<li><p><strong>00:01.108</strong>: <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></li>
-<li><p><strong>00:00.219</strong>: <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></li>
+<li><p><strong>00:34.362</strong>: <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></li>
+<li><p><strong>00:02.205</strong>: <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></li>
+<li><p><strong>00:01.020</strong>: <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></li>
+<li><p><strong>00:00.183</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index f4552d333..fa7714475 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6279us [6279us] (45.53%; 45.53%)
-FoldScaleAxis: 7513us [2us] (54.47%; 54.47%)
- FoldConstant: 7510us [1536us] (54.45%; 99.97%)
- InferType: 5975us [5975us] (43.32%; 79.55%)
+InferType: 6252us [6252us] (45.55%; 45.55%)
+FoldScaleAxis: 7472us [2us] (54.45%; 54.45%)
+ FoldConstant: 7470us [1557us] (54.43%; 99.97%)
+ InferType: 5913us [5913us] (43.08%; 79.15%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6086us [6086us] (45.14%; 45.14%)
-FoldScaleAxis: 7397us [2us] (54.86%; 54.86%)
- FoldConstant: 7394us [1538us] (54.84%; 99.97%)
- InferType: 5857us [5857us] (43.44%; 79.20%)
+InferType: 6009us [6009us] (44.66%; 44.66%)
+FoldScaleAxis: 7447us [2us] (55.34%; 55.34%)
+ FoldConstant: 7445us [1539us] (55.33%; 99.98%)
+ InferType: 5906us [5906us] (43.89%; 79.33%)
</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 e4f83d14c..50b10d925 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.692116 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.099805 ms
</pre></div>
</div>
<div class="sphx-glr-footer class 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 67f30f108..61d6c398d 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.044295 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.581543 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 82dc5e42f..5a354908e 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019797
-Baseline: 3.581554
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018160
+Baseline: 3.412251
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.332761
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300460
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.348876
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.338944
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.135626
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115266
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112655
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110973
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.113771
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.112382
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.147764
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145613
</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 60ab27f81..1331dd06f 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:36.802</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.834</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.095</strong>: <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></li>
-<li><p><strong>00:01.479</strong>: <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></li>
-<li><p><strong>00:01.228</strong>: <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></li>
+<li><p><strong>00:32.388</strong>: <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></li>
+<li><p><strong>00:01.321</strong>: <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></li>
+<li><p><strong>00:01.126</strong>: <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></li>
</ul>
</div>
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 a4edf0ee4..38f99aa9d 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<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>05:07.609</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>03:34.764</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:27.970</strong>: <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></li>
-<li><p><strong>01:21.333</strong>: <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></li>
-<li><p><strong>00:41.741</strong>: <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></li>
-<li><p><strong>00:18.350</strong>: <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></li>
-<li><p><strong>00:09.260</strong>: <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></li>
-<li><p><strong>00:08.955</strong>: <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></li>
+<li><p><strong>01:19.186</strong>: <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></li>
+<li><p><strong>01:07.420</strong>: <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></li>
+<li><p><strong>00:40.742</strong>: <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></li>
+<li><p><strong>00:09.466</strong>: <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></li>
+<li><p><strong>00:09.319</strong>: <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></li>
+<li><p><strong>00:08.630</strong>: <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></li>
</ul>
</div>
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 e323fb120..34865f727 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
@@ -470,910 +470,483 @@ 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" = 64;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[6] = 0f32
+ 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
+ conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (rc.outer.outer*288)
- let cse_var_2: int32 = (ry.outer.outer*7)
+ 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" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((t [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 196), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 197)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 197), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 198)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 146)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 199)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 199), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 392), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 393)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 393), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 394)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 394), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 395)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 395), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 588), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 589)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 589), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 590)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 590), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 591)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 591), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 784), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 785)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 785), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 786)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 786), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 787)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 787), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 980), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 981)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 755)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 982)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 982), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 983)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 983), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1176), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1177)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1177), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1178)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1178), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1179)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 909)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1372), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1373)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1373), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1374)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1374), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1375)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1375), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1568), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1569)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1569), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1570)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1570), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1571)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1571), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1364)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1765)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1765), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1766)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1766), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1767)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1767), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1960), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), [...]
+ 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 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1961)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1961), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), [...]
+ 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 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1962)] = @tir.if_then_else(((((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1518)], 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)], 0 [...]
}
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1963)] = @tir.if_then_else(((((floordiv(floormod(((threadIdx.x_1*4) + 1963), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1963), 9)*7)) + cse_var_2) + 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) + 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 [...]
}
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 98), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 196), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 245), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 343), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 19), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 490), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 539), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 637), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 686), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 33), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 21), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[0]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[192]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[384]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[576]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[1]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[193]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[385]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[577]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[2]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[194]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[386]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[578]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[3]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[195]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[387]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[579]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[4]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[196]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[388]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[580]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[5]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[197]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[389]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[581]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[6]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[198]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[390]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[582]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[7]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[199]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[391]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[583]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[8]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[200]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[392]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[584]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[9]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[201]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[393]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[585]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[10]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[202]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[394]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[586]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[11]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[203]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[395]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[587]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[12]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[204]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[396]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[588]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[13]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[205]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[397]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[589]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[14]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[206]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[398]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[590]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[15]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[207]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[399]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[591]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[16]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[208]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[400]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[592]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[17]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[209]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[401]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[593]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[18]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[210]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[402]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[594]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[19]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[211]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[403]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[595]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[20]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[212]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[404]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[596]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[21]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[213]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[405]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[597]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[22]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[214]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[406]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[598]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[23]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[215]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[407]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[599]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[24]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[216]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[408]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[600]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[25]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[217]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[409]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[601]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[26]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[218]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[410]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[602]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[27]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[219]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[411]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[603]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[28]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[220]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[412]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[604]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[29]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[221]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[413]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[605]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[30]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[222]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[414]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[606]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[31]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[223]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[415]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[607]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[32]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[224]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[416]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[608]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[33]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[225]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[417]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[609]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[34]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[226]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[418]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[610]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[35]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[227]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[419]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[611]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[36]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[228]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[420]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[612]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[37]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[229]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[421]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[613]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[38]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[230]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[422]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[614]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[39]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[231]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[423]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[615]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[40]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[232]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[424]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[616]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[41]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[233]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[425]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[617]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[42]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[234]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[426]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[618]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[43]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[235]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[427]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[619]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[44]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[236]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[428]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[620]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[45]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[237]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[429]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[621]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[46]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[238]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[430]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[622]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[47]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[239]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[431]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[623]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[48]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[240]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[432]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[624]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[49]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[241]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[433]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[625]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[50]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[242]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[434]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[626]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[51]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[243]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[435]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[627]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[52]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[244]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[436]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[628]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[53]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[245]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[437]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[629]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[54]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[246]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[438]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[630]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[55]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[247]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[439]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[631]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[56]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[248]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[440]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[632]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[57]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[249]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[441]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[633]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[58]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[250]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[442]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[634]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[59]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[251]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[443]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[635]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[60]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[252]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[444]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[636]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[61]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[253]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[445]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[637]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[62]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[254]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[446]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[638]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[63]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[255]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[447]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[639]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[64]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[256]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[448]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[640]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[65]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[257]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[449]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[641]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[66]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[258]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[450]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[642]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[67]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[259]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[451]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[643]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[68]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[260]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[452]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[644]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[69]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[261]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[453]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[645]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[70]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[262]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[454]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[646]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[71]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[263]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[455]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[647]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[72]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[264]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[456]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[648]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[73]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[265]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[457]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[649]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[74]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[266]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[458]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[650]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[75]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[267]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[459]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[651]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[76]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[268]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[460]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[652]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[77]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[269]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[461]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[653]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[78]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[270]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[462]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[654]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[79]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[271]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[463]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[655]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[80]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[272]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[464]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[656]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[81]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[273]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[465]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[657]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[82]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[274]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[466]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[658]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[83]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[275]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[467]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[659]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[84]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[276]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[468]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[660]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[85]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[277]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[469]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[661]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[86]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[278]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[470]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[662]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[87]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[279]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[471]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[663]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[88]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[280]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[472]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[664]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[89]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[281]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[473]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[665]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[90]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[282]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[474]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[666]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[91]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[283]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[475]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[667]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[92]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[284]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[476]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[668]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[93]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[285]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[477]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[669]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[94]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[286]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[478]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[670]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[95]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[287]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[479]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[671]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[96]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[288]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[480]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[672]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[97]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[289]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[481]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[673]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[98]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[290]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[482]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[674]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[99]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[291]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[483]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[675]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[100]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[292]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[484]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[676]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[101]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[293]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[485]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[677]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[102]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[294]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[486]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[678]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[103]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[295]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[487]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[679]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[104]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[296]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[488]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[680]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[105]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[297]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[489]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[681]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[106]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[298]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[490]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[682]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[107]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[299]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[491]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[683]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[108]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[300]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[492]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[684]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[109]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[301]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[493]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[685]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[110]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[302]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[494]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[686]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[111]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[303]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[495]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[687]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[112]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[304]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[496]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[688]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[113]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[305]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[497]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[689]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[114]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[306]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[498]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[690]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[115]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[307]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[499]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[691]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[116]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[308]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[500]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[692]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[117]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[309]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[501]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[693]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[118]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[310]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[502]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[694]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[119]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[311]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[503]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[695]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[120]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[312]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[504]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[696]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[121]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[313]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[505]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[697]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[122]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[314]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[506]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[698]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[123]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[315]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[507]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[699]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[124]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[316]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[508]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[700]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[125]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[317]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[509]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[701]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[126]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[318]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[510]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 630)]*kernel.shared_1[702]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[127]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[319]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[511]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 631)]*kernel.shared_1[703]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[128]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[320]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[512]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 632)]*kernel.shared_1[704]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[129]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[321]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[513]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 693)]*kernel.shared_1[705]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[130]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[322]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[514]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 694)]*kernel.shared_1[706]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[131]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[323]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[515]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 695)]*kernel.shared_1[707]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[132]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[324]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[516]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 756)]*kernel.shared_1[708]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[133]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[325]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[517]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 757)]*kernel.shared_1[709]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[134]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[326]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[518]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 758)]*kernel.shared_1[710]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[135]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[327]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[519]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[711]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[136]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[328]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[520]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[712]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[137]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[329]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[521]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[713]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[138]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[330]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[522]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 882)]*kernel.shared_1[714]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[139]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[331]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[523]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 883)]*kernel.shared_1[715]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[140]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[332]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[524]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 884)]*kernel.shared_1[716]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[141]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[333]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[525]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 945)]*kernel.shared_1[717]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[142]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[334]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[526]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 946)]*kernel.shared_1[718]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[143]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[335]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[527]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 947)]*kernel.shared_1[719]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[144]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[336]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[528]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1008)]*kernel.shared_1[720]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[145]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[337]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[529]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1009)]*kernel.shared_1[721]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[146]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[338]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[530]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1010)]*kernel.shared_1[722]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[147]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[339]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[531]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[723]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[148]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[340]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[532]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[724]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[149]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[341]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[533]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[725]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[150]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[342]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[534]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[726]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[151]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[343]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[535]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[727]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[152]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[344]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[536]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[728]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[153]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[345]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[537]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1197)]*kernel.shared_1[729]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[154]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[346]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[538]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1198)]*kernel.shared_1[730]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[155]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[347]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[539]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1199)]*kernel.shared_1[731]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[156]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[348]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[540]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1260)]*kernel.shared_1[732]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[157]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[349]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[541]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1261)]*kernel.shared_1[733]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[158]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[350]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[542]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1262)]*kernel.shared_1[734]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[159]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[351]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[543]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1323)]*kernel.shared_1[735]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[160]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[352]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[544]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1324)]*kernel.shared_1[736]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[161]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[353]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[545]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1325)]*kernel.shared_1[737]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[162]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[354]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[546]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1386)]*kernel.shared_1[738]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[163]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[355]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[547]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1387)]*kernel.shared_1[739]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[164]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[356]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[548]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1388)]*kernel.shared_1[740]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[165]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[357]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[549]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1449)]*kernel.shared_1[741]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[166]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[358]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[550]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1450)]*kernel.shared_1[742]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[167]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[359]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[551]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1451)]*kernel.shared_1[743]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[168]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[360]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[552]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1512)]*kernel.shared_1[744]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[169]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[361]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[553]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1513)]*kernel.shared_1[745]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[170]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[362]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[554]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1514)]*kernel.shared_1[746]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[171]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[363]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[555]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1575)]*kernel.shared_1[747]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[172]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[364]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[556]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1576)]*kernel.shared_1[748]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[173]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[365]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[557]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1577)]*kernel.shared_1[749]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[174]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[366]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[558]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1638)]*kernel.shared_1[750]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[175]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[367]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[559]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1639)]*kernel.shared_1[751]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[176]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[368]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[560]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1640)]*kernel.shared_1[752]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[177]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[369]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[561]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1701)]*kernel.shared_1[753]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[178]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[370]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[562]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1702)]*kernel.shared_1[754]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[179]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[371]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[563]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1703)]*kernel.shared_1[755]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[180]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[372]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[564]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1764)]*kernel.shared_1[756]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[181]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[373]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[565]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1765)]*kernel.shared_1[757]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[182]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[374]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[566]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1766)]*kernel.shared_1[758]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[183]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[375]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[567]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1827)]*kernel.shared_1[759]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[184]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[376]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[568]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1828)]*kernel.shared_1[760]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[185]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[377]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[569]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1829)]*kernel.shared_1[761]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[186]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[378]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[570]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1890)]*kernel.shared_1[762]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[187]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[379]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[571]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1891)]*kernel.shared_1[763]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[188]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[380]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[572]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1892)]*kernel.shared_1[764]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[189]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[381]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[573]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1953)]*kernel.shared_1[765]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[190]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[382]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[574]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1954)]*kernel.shared_1[766]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[191]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[383]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[575]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(threadIdx.x, 7)*9) + floormod(threadIdx.x, 7)) + 1955)]*kernel.shared_1[767]))
+ 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((floordiv(threadIdx.x_2, 8) + 8), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 64), 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((floordiv(threadIdx.x_2, 8) + 16), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 128), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 32), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 256), 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((floordiv(threadIdx.x_2, 8) + 40), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 320), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 448), 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((floordiv(threadIdx.x_2, 8) + 64), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 512), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 80), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 640), 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((floordiv(threadIdx.x_2, 8) + 88), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 704), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 104), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 832), 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((floordiv(threadIdx.x_2, 8) + 112), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 896), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 128), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1024), 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((floordiv(threadIdx.x_2, 8) + 136), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1088), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 152), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1216), 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((floordiv(threadIdx.x_2, 8) + 160), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1280), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 176), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1408), 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((floordiv(threadIdx.x_2, 8) + 184), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1472), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 200), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1600), 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((floordiv(threadIdx.x_2, 8) + 208), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1664), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 224), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1792), 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((floordiv(threadIdx.x_2, 8) + 232), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1856), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 248), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 1984), 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((floordiv(threadIdx.x_2, 8) + 256), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2048), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 272), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2176), 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((floordiv(threadIdx.x_2, 8) + 280), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2240), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 296), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2368), 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((floordiv(threadIdx.x_2, 8) + 304), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2432), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 320), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2560), 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((floordiv(threadIdx.x_2, 8) + 328), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2624), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 344), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2752), 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((floordiv(threadIdx.x_2, 8) + 352), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2816), 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(floordiv(threadIdx.x_2, 8), 3)*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((floordiv(threadIdx.x_2, 8) + 368), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 2944), 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((floordiv(threadIdx.x_2, 8) + 376), 3)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 3008), 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) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 98)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((blockIdx.x*8) + i1.inner) + 2)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*8) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x) + 294)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((blockIdx.x*8) + i1.inner) + 6)]), 0f32)
+ 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)
+ }
}
}
}
@@ -1411,7 +984,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.237 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.360 ms
</pre></div>
</div>
</div>
@@ -1443,34 +1016,34 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
-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=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=64)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=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_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
-conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=32)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_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_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=64)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
-compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -1490,14 +1063,14 @@ 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=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=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=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=64)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1515,867 +1088,430 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[768];
+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];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[6] = 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;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 196)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 197)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 197) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 198)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 146)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 199)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 199) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 394)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 395)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 395) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 588)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 589)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 590)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 591)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 591) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 786)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 786) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 787)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 787) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 980)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 981)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 755)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 982)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 982) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 983)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 983) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1178) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1179)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 909)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1372)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1373)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1373) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1374)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1374) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1375)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1375) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1570)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1570) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1571)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1571) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1764)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1765)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1765) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1766)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1766) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1767)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1767) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1960)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1961)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] [...]
+ 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) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1962)] = (((((ry_outer_outer + (((((int)threadIdx.x) * 4) / 9) + 1)) < 8) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1518)] : 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) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1963)] = (((((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1963) / 9) * 7)) + (ry_outer_outer * 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);
}
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 2) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 4) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 33) {
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 21) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 18) {
+ pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (ry_outer_outer + (((int)blockIdx.x) % 7))) && ((ry_outer_outer + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 49)) + (ry_outer_outer * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 64) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 320) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 704) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 832) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1088) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1216) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1472) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1600) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 331776)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1856) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1984) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 405504)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2240) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2368) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 479232)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2624) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2752) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[((((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 552960)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3008) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 8) % 24) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[0]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[192]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[384]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[576]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[1]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[193]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[385]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[577]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[2]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[194]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[386]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[578]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[3]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[195]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[387]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[579]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[4]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[196]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[388]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[580]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[5]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[197]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[389]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[581]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[6]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[198]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[390]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[582]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[7]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[199]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[391]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[583]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[8]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[200]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[392]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[584]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[9]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[201]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[393]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[585]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[10]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[202]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[394]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[586]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[11]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[203]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[395]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[587]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[12]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[204]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[396]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[588]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[13]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[205]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[397]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[589]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[14]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[206]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[398]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[590]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[15]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[207]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[399]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[591]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[16]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[208]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[400]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[592]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[17]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[209]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[401]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[593]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[18]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[210]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[402]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[594]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[19]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[211]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[403]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[595]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[20]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[212]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[404]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[596]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[21]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[213]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[405]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[597]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[22]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[214]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[406]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[598]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[23]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[215]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[407]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[599]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[24]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[216]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[408]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[600]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[25]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[217]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[409]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[601]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[26]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[218]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[410]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[602]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[27]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[219]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[411]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[603]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[28]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[220]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[412]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[604]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[29]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[221]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[413]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[605]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[30]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[222]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[414]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[606]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[31]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[223]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[415]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[607]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[32]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[224]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[416]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[608]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[33]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[225]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[417]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[609]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[34]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[226]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[418]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[610]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[35]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[227]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[419]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[611]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[36]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[228]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[420]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[612]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[37]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[229]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[421]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[613]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[38]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[230]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[422]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[614]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[39]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[231]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[423]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[615]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[40]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[232]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[424]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[616]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[41]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[233]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[425]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[617]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[42]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[234]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[426]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[618]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[43]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[235]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[427]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[619]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[44]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[236]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[428]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[620]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[45]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[237]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[429]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[621]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[46]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[238]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[430]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[622]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[47]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[239]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[431]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[623]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[48]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[240]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[432]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[624]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[49]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[241]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[433]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[625]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[50]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[242]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[434]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[626]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[51]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[243]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[435]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[627]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[52]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[244]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[436]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[628]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[53]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[245]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[437]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[629]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[54]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[246]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[438]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[630]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[55]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[247]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[439]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[631]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[56]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[248]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[440]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[632]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[57]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[249]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[441]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[633]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[58]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[250]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[442]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[634]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[59]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[251]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[443]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[635]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[60]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[252]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[444]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[636]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[61]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[253]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[445]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[637]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[62]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[254]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[446]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[638]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[63]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[255]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[447]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[639]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[64]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[256]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[448]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[640]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[65]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[257]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[449]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[641]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[66]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[258]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[450]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[642]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[67]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[259]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[451]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[643]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[68]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[260]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[452]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[644]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[69]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[261]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[453]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[645]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[70]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[262]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[454]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[646]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[71]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[263]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[455]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[647]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[72]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[264]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[456]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[648]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[73]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[265]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[457]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[649]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[74]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[266]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[458]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[650]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[75]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[267]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[459]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[651]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[76]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[268]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[460]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[652]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[77]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[269]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[461]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[653]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[78]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[270]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[462]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[654]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[79]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[271]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[463]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[655]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[80]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[272]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[464]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[656]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[81]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[273]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[465]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[657]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[82]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[274]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[466]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[658]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[83]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[275]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[467]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[659]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[84]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[276]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[468]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[660]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[85]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[277]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[469]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[661]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[86]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[278]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[470]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[662]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[87]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[279]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[471]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[663]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[88]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[280]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[472]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[664]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[89]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[281]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[473]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[665]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[90]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[282]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[474]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[666]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[91]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[283]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[475]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[667]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[92]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[284]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[476]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[668]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[93]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[285]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[477]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[669]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[94]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[286]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[478]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[670]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[95]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[287]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[479]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[671]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[96]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[288]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[480]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[672]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[97]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[289]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[481]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[673]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[98]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[290]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[482]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[674]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[99]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[291]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[483]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[675]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[100]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[292]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[484]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[676]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[101]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[293]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[485]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[677]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[102]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[294]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[486]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[678]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[103]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[295]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[487]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[679]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[104]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[296]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[488]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[680]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[105]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[297]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[489]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[681]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[106]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[298]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[490]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[682]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[107]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[299]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[491]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[683]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[108]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[300]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[492]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[684]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[109]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[301]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[493]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[685]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[110]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[302]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[494]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[686]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[111]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[303]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[495]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[687]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[112]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[304]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[496]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[688]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[113]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[305]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[497]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[689]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[114]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[306]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[498]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[690]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[115]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[307]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[499]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[691]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[116]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[308]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[500]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[692]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[117]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[309]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[501]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[693]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[118]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[310]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[502]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[694]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[119]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[311]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[503]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[695]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[120]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[312]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[504]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[696]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[121]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[313]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[505]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[697]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[122]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[314]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[506]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[698]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[123]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[315]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[507]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[699]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[124]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[316]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[508]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[700]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[125]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[317]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[509]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[701]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[126]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[318]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[510]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 630)] * kernel_shared[702]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[127]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[319]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[511]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 631)] * kernel_shared[703]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[128]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[320]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[512]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 632)] * kernel_shared[704]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[129]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[321]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[513]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 693)] * kernel_shared[705]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[130]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[322]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[514]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 694)] * kernel_shared[706]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[131]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[323]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[515]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 695)] * kernel_shared[707]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[132]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[324]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[516]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 756)] * kernel_shared[708]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[133]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[325]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[517]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 757)] * kernel_shared[709]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[134]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[326]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[518]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 758)] * kernel_shared[710]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[135]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[327]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[519]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[711]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[136]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[328]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[520]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[712]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[137]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[329]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[521]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[713]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[138]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[330]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[522]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 882)] * kernel_shared[714]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[139]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[331]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[523]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 883)] * kernel_shared[715]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[140]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[332]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[524]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 884)] * kernel_shared[716]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[141]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[333]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[525]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 945)] * kernel_shared[717]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[142]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[334]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[526]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 946)] * kernel_shared[718]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[143]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[335]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[527]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 947)] * kernel_shared[719]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[144]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[336]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[528]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1008)] * kernel_shared[720]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[145]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[337]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[529]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1009)] * kernel_shared[721]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[146]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[338]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[530]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1010)] * kernel_shared[722]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[147]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[339]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[531]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[723]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[148]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[340]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[532]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[724]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[149]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[341]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[533]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[725]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[150]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[342]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[534]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[726]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[151]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[343]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[535]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[727]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[152]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[344]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[536]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[728]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[153]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[345]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[537]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1197)] * kernel_shared[729]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[154]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[346]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[538]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1198)] * kernel_shared[730]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[155]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[347]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[539]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1199)] * kernel_shared[731]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[156]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[348]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[540]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1260)] * kernel_shared[732]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[157]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[349]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[541]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1261)] * kernel_shared[733]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[158]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[350]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[542]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1262)] * kernel_shared[734]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[159]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[351]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[543]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1323)] * kernel_shared[735]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[160]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[352]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[544]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1324)] * kernel_shared[736]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[161]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[353]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[545]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1325)] * kernel_shared[737]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[162]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[354]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[546]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1386)] * kernel_shared[738]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[163]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[355]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[547]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1387)] * kernel_shared[739]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[164]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[356]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[548]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1388)] * kernel_shared[740]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[165]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[357]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[549]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1449)] * kernel_shared[741]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[166]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[358]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[550]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1450)] * kernel_shared[742]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[167]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[359]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[551]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1451)] * kernel_shared[743]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[168]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[360]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[552]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1512)] * kernel_shared[744]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[169]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[361]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[553]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1513)] * kernel_shared[745]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[170]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[362]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[554]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1514)] * kernel_shared[746]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[171]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[363]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[555]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1575)] * kernel_shared[747]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[172]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[364]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[556]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1576)] * kernel_shared[748]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[173]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[365]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[557]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1577)] * kernel_shared[749]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[174]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[366]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[558]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1638)] * kernel_shared[750]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[175]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[367]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[559]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1639)] * kernel_shared[751]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[176]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[368]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[560]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1640)] * kernel_shared[752]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[177]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[369]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[561]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1701)] * kernel_shared[753]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[178]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[370]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[562]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1702)] * kernel_shared[754]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[179]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[371]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[563]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1703)] * kernel_shared[755]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[180]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[372]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[564]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1764)] * kernel_shared[756]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[181]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[373]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[565]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1765)] * kernel_shared[757]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[182]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[374]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[566]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1766)] * kernel_shared[758]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[183]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[375]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[567]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1827)] * kernel_shared[759]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[184]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[376]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[568]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1828)] * kernel_shared[760]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[185]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[377]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[569]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1829)] * kernel_shared[761]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[186]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[378]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[570]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1890)] * kernel_shared[762]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[187]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[379]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[571]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1891)] * kernel_shared[763]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[188]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[380]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[572]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1892)] * kernel_shared[764]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[189]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[381]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[573]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1953)] * kernel_shared[765]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[190]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[382]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[574]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1954)] * kernel_shared[766]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[191]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[383]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[575]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((int)threadIdx.x) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1955)] * kernel_shared[767]));
+ 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) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 98)] = max((conv2d_nchw[(i1_inner + 2)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 2)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x)) + 294)] = max((conv2d_nchw[(i1_inner + 6)] + bias[(((((int)blockIdx.x) * 8) + i1_inner) + 6)]), 0.000000e+00f);
+ for (int i3_inner = 0; i3_inner < 7; ++i3_inner) {
+ compute[((((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + i3_inner)] = max((conv2d_nchw[((i1_inner * 7) + i3_inner)] + bias[((((((int)blockIdx.x) / 7) * 128) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ }
}
}
</pre></div>
@@ -2413,7 +1549,7 @@ 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 27.970 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.420 seconds)</p>
<div class="sphx-glr-footer class 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 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 b64ac1587..1f6deddc1 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -878,7 +878,7 @@ 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)
- 9.7115 9.7256 9.7285 9.6803 0.0221
+ 9.8776 9.8787 9.8992 9.8548 0.0181
</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 497ba55eb..f21e56cbb 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -897,7 +897,7 @@ 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)
- 781.7172 781.8939 782.0381 781.2196 0.3568
+ 754.5500 757.0768 758.6450 747.9284 4.7258
</pre></div>
</div>
</div>
@@ -919,7 +919,7 @@ 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 21.333 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.186 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download 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 8677febd1..4f1b3e1bf 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,77 +600,28 @@ 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.i1.outer.fused: int32, 0, 32) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [2048]), storage_scope = global {
- for (i.outer.inner: int32, 0, 4) {
- for (i.inner.init: int32, 0, 32) {
- let cse_var_1: int32 = ((i.outer.inner*512) + (i.inner.init*16))
- {
- compute_5: Buffer(compute_4, float32, [2048], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 8) {
+ for (i.inner.init: int32, 0, 8) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.outer.inner*128) + (i.inner.init*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, (placeholder_3[(i0.outer.i1.outer.fused + 1)] - placeholder_3[i0.outer.i1.outer.fused])) {
- for (i.inner: int32, 0, 32) {
- let cse_var_19: int32 = (elem_idx*16)
- let cse_var_18: int32 = ((i.outer.inner*8192) + (i.inner*256))
- let cse_var_17: int32 = ((i.outer.inner*512) + (i.inner*16))
- let cse_var_16: int32 = (cse_var_17 + 1)
- let cse_var_15: int32 = (cse_var_17 + 11)
- let cse_var_14: int32 = (cse_var_17 + 12)
- let cse_var_13: int32 = (cse_var_17 + 13)
- let cse_var_12: int32 = (cse_var_17 + 14)
- let cse_var_11: int32 = (cse_var_17 + 15)
- let cse_var_10: int32 = (cse_var_17 + 2)
- let cse_var_9: int32 = (cse_var_17 + 3)
- let cse_var_8: int32 = (cse_var_17 + 4)
- let cse_var_7: int32 = (cse_var_17 + 5)
- let cse_var_6: int32 = (cse_var_17 + 6)
- let cse_var_5: int32 = (cse_var_17 + 7)
- let cse_var_4: int32 = (cse_var_17 + 8)
- let cse_var_3: int32 = (cse_var_17 + 9)
- let cse_var_2: int32 = (cse_var_17 + 10)
- {
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i0.outer.i1.outer.fused]*16) + cse_var_19) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[i0.outer.i1.outer.fused] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 8) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = (((i.outer.inner*128) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i.outer.inner*2048)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 128) {
- for (i1.inner: int32, 0, 16) {
- let cse_var_20: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*16)) + i1.inner)
- compute[cse_var_20] = max((compute_5[((i0.inner*16) + i1.inner)] + placeholder_4[cse_var_20]), 0f32)
- }
+ for (i0.inner: int32, 0, 64) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*32768) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -709,7 +660,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.844 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.533 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 0686b9f7c..de5740641 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:45.088</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:46.558</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.137</strong>: <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></li>
-<li><p><strong>00:00.249</strong>: <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></li>
-<li><p><strong>00:00.235</strong>: <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></li>
-<li><p><strong>00:00.234</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.232</strong>: <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></li>
+<li><p><strong>00:45.737</strong>: <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></li>
+<li><p><strong>00:00.222</strong>: <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></li>
+<li><p><strong>00:00.208</strong>: <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></li>
+<li><p><strong>00:00.196</strong>: <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></li>
+<li><p><strong>00:00.195</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
</ul>
</div>
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 41cf41b43..62cbb0efd 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 101.91/101.91 result: MeasureResult(costs=(0.002271515416666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6228275299072266, timestamp=1653702966.3588765) [('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: 0.00/101.91 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.26/42.26 result: MeasureResult(costs=(0.005478168421052631,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8430910110473633, timestamp=1653702431.0350013) [('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: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.26 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
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/101.91 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, 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: 0.00/101.91 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.26 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9c664cdfa2
+ 12: 0x00007f2c7323bfa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ 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: 144.25/144.25 result: MeasureResult(costs=(0.00160487599,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4451184272766113, timestamp=1653702992.3415928) [('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: 143.81/143.81 result: MeasureResult(costs=(0.00160972107,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3969709873199463, timestamp=1653702450.6702278) [('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,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>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
-Time cost of this operator: 0.002033
+Time cost of this operator: 0.002015
</pre></div>
</div>
<div class="sphx-glr-footer class 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 dd6ac45e8..131bc46ec 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -555,10 +555,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.0 98.744 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.079 0.971 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.284 (1, 1, 10, 10, 3) 1 1
-Total_time - 316.981 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.3 98.755 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.955 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.911 0.29 (1, 1, 10, 10, 3) 1 1
+Total_time - 314.211 - - - -
</pre></div>
</div>
</div>
@@ -610,10 +610,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 228.8 98.795 (1, 1, 10, 10, 6) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.967 0.849 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.823 0.355 (1, 3, 10, 10, 1) 1 1
-Total_time - 231.59 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 194.3 98.729 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.702 0.865 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.8 0.407 (1, 3, 10, 10, 1) 1 1
+Total_time - 196.802 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class 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/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 1c5d21946..5387e29fe 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<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>00:48.727</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:46.418</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.241</strong>: <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></li>
-<li><p><strong>00:03.829</strong>: <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></li>
-<li><p><strong>00:00.227</strong>: <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></li>
-<li><p><strong>00:00.217</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
-<li><p><strong>00:00.213</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:42.338</strong>: <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></li>
+<li><p><strong>00:03.529</strong>: <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></li>
+<li><p><strong>00:00.192</strong>: <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></li>
+<li><p><strong>00:00.182</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.177</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
</ul>
</div>
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 bf94d8bc0..416878e65 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<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>00:12.578</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:05.292</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:10.426</strong>: <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></li>
-<li><p><strong>00:01.919</strong>: <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></li>
-<li><p><strong>00:00.233</strong>: <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></li>
+<li><p><strong>00:03.670</strong>: <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></li>
+<li><p><strong>00:01.411</strong>: <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></li>
+<li><p><strong>00:00.211</strong>: <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></li>
</ul>
</div>
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 4901edf89..b67365aad 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<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>00:06.167</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.311</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.217</strong>: <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></li>
-<li><p><strong>00:01.276</strong>: <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></li>
-<li><p><strong>00:00.767</strong>: <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></li>
-<li><p><strong>00:00.762</strong>: <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></li>
-<li><p><strong>00:00.333</strong>: <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></li>
-<li><p><strong>00:00.311</strong>: <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></li>
-<li><p><strong>00:00.257</strong>: <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></li>
-<li><p><strong>00:00.244</strong>: <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></li>
+<li><p><strong>00:02.043</strong>: <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></li>
+<li><p><strong>00:00.875</strong>: <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></li>
+<li><p><strong>00:00.701</strong>: <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></li>
+<li><p><strong>00:00.692</strong>: <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></li>
+<li><p><strong>00:00.300</strong>: <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></li>
+<li><p><strong>00:00.243</strong>: <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></li>
+<li><p><strong>00:00.233</strong>: <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></li>
+<li><p><strong>00:00.225</strong>: <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></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 8b3bf534f..ed51b2f8a 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ 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/tmp2f8oh8hc/input0.cc'\nsource_filename = \"/tmp/tmp2f8oh8hc/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/tmpxqu7735t/input0.cc'\nsource_filename = \"/tmp/tmpxqu7735t/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/doxygen/arg__info_8h_source.html b/docs/reference/api/doxygen/arg__info_8h_source.html
index 4440c35c6..bc6bf6cc1 100644
--- a/docs/reference/api/doxygen/arg__info_8h_source.html
+++ b/docs/reference/api/doxygen/arg__info_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfo_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfo.html">tvm::meta_schedule::TensorInfo</a></div><div class="ttdoc">Managed reference to TensorInfoNode. </div><div class="ttdef"><b>Definition:</b> arg_info.h:91</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfoNode_html"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html">tvm::meta_schedule::TensorInfoNode</a></div><div class="ttdoc">The tensor argument information. </div><div class="ttdef"><b>Definition:</b> arg_info.h:68</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfoNode_html_ab54cd62d85a051b78c9605ac0d2d3cb7"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html#ab54cd62d85a051b78c9605ac0d2d3cb7">tvm::meta_schedule::TensorInfoNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> arg_info.h:75</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="classtvm_1_1meta__schedule_1_1TensorInfoNode_html_a703cc684f922c4c7dddb20a503a78eb9"><div class="ttname"><a href="classtvm_1_1meta__schedule_1_1TensorInfoNode.html#a703cc684f922c4c7dddb20a503a78eb9">tvm::meta_schedule::TensorInfoNode::dtype</a></div><div class="ttdeci">runtime::DataType dtype</div><div class="ttdoc">The data type of the tensor. </div><div class="ttdef"><b>Definition:</b> arg_info.h:71</div></div>
<div class="ttc" id="shape__tuple_8h_html"><div class="ttname"><a href="shape__tuple_8h.html">shape_tuple.h</a></div><div class="ttdoc">Runtime ShapeTuple container types. </div></div>
diff --git a/docs/reference/api/doxygen/bytecode_8h_source.html b/docs/reference/api/doxygen/bytecode_8h_source.html
index 66ef787e8..3b39ff693 100644
--- a/docs/reference/api/doxygen/bytecode_8h_source.html
+++ b/docs/reference/api/doxygen/bytecode_8h_source.html
@@ -111,7 +111,7 @@ $(function() {
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a46879dbe84105fb621a6167f8d73b223"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a46879dbe84105fb621a6167f8d73b223">tvm::runtime::vm::Instruction::target</a></div><div class="ttdeci">RegName target</div><div class="ttdoc">The register containing the target value. </div><div class="ttdef"><b>Definition:</b> bytecode.h:143</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a360b264ed892e620935b648e5a91a5ea"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a360b264ed892e620935b648e5a91a5ea">tvm::runtime::vm::Instruction::arity</a></div><div class="ttdeci">Index arity</div><div class="ttdoc">The arity of the packed function. </div><div class="ttdef"><b>Definition:</b> bytecode.h:133</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a3a175836bc0893d99935f32911e45bfd"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3a175836bc0893d99935f32911e45bfd">tvm::runtime::vm::Instruction::closure</a></div><div class="ttdeci">RegName closure</div><div class="ttdoc">The register containing the closure. </div><div class="ttdef"><b>Definition:</b> bytecode.h:115</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a3412cabd3b4f42f106f56fc22257f6ca"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a3412cabd3b4f42f106f56fc22257f6ca">tvm::runtime::vm::Instruction::storage</a></div><div class="ttdeci">RegName storage</div><div class="ttdoc">The storage to allocate from. </div><div class="ttdef"><b>Definition:</b> bytecode.h:93</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1vm_html_a3597867d2db714bf760876a23d6b7d3d"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1vm.html#a3597867d2db714bf760876a23d6b7d3d">tvm::runtime::vm::Index</a></div><div class="ttdeci">int64_t Index</div><div class="ttdoc">An alias for the integer type used ubiquitously in the VM. </div><div class="ttdef"><b>Definition:</b> bytecode.h:43</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Instruction_html_a5d98a3b5b50e6fa9029d05f741c0bce9"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Instruction.html#a5d98a3b5b50e6fa9029d05f741c0bce9">tvm::runtime::vm::Instruction::num_args</a></div><div class="ttdeci">Index num_args</div><div class="ttdoc">The number of arguments to the function. </div><div class="ttdef"><b>Definition:</b> bytecode.h:153</div></div>
diff --git a/docs/reference/api/doxygen/c__runtime__api_8h_source.html b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
index 19d6daabc..d1d728b44 100644
--- a/docs/reference/api/doxygen/c__runtime__api_8h_source.html
+++ b/docs/reference/api/doxygen/c__runtime__api_8h_source.html
@@ -126,7 +126,7 @@ $(function() {
<div class="ttc" id="c__runtime__api_8h_html_ae690840d1af9c7b0fe5b9b457456f60d"><div class="ttname"><a href="c__runtime__api_8h.html#ae690840d1af9c7b0fe5b9b457456f60d">TVMArrayToDLPack</a></div><div class="ttdeci">int TVMArrayToDLPack(TVMArrayHandle from, DLManagedTensor **out)</div><div class="ttdoc">Produce a DLMangedTensor from the array that shares data memory with the array. </div></div>
<div class="ttc" id="c__runtime__api_8h_html_a6cd1076476117e74454f67931c2da1d4"><div class="ttname"><a href="c__runtime__api_8h.html#a6cd1076476117e74454f67931c2da1d4">TVMRetValueHandle</a></div><div class="ttdeci">void * TVMRetValueHandle</div><div class="ttdoc">Handle to hold return value. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:167</div></div>
<div class="ttc" id="c__runtime__api_8h_html_acf57d257a6e0841d84ebbd2a339d183e"><div class="ttname"><a href="c__runtime__api_8h.html#acf57d257a6e0841d84ebbd2a339d183e">TVMFunctionHandle</a></div><div class="ttdeci">void * TVMFunctionHandle</div><div class="ttdoc">Handle to packed function handle. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:165</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ace8007daffd9f2c6d954c24d870bfcc4"><div class="ttname"><a href="c__runtime__api_8h.html#ace8007daffd9f2c6d954c24d870bfcc4">tvm_index_t</a></div><div class="ttdeci">int64_t tvm_index_t</div><div class="ttdoc">type of array index. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:81</div></div>
<div class="ttc" id="c__runtime__api_8h_html_a190e81769e805cca153514137a66e793a9387f774bc8453afe4aa4cd17789a405"><div class="ttname"><a href="c__runtime__api_8h.html#a190e81769e805cca153514137a66e793a9387f774bc8453afe4aa4cd17789a405">kTVMOpaqueHandle</a></div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:113</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ae899a6a211b7913e92420a01b804db64"><div class="ttname"><a href="c__runtime__api_8h.html#ae899a6a211b7913e92420a01b804db64">TVMObjectRetain</a></div><div class="ttdeci">int TVMObjectRetain(TVMObjectHandle obj)</div><div class="ttdoc">Increase the reference count of an object. </div></div>
diff --git a/docs/reference/api/doxygen/data__layout_8h_source.html b/docs/reference/api/doxygen/data__layout_8h_source.html
index 16c30d28d..cf6747bec 100644
--- a/docs/reference/api/doxygen/data__layout_8h_source.html
+++ b/docs/reference/api/doxygen/data__layout_8h_source.html
@@ -94,7 +94,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html">tvm::runtime::Array</a></div><div class="ttdoc">Array, container representing a contiguous sequence of ObjectRefs. </div><div class="ttdef"><b>Definition:</b> array.h:270</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html_a7fd4348d39ad4249daf89d54195fa65a"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a7fd4348d39ad4249daf89d54195fa65a">tvm::tir::Layout::ndim</a></div><div class="ttdeci">size_t ndim() const</div><div class="ttdef"><b>Definition:</b> data_layout.h:178</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BijectiveLayoutNode_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BijectiveLayoutNode.html">tvm::tir::BijectiveLayoutNode</a></div><div class="ttdef"><b>Definition:</b> data_layout.h:293</div></div>
<div class="ttc" id="namespacetvm_1_1te_html_ae0c71f84710b436cbe0b32289d0838f4"><div class="ttname"><a href="namespacetvm_1_1te.html#ae0c71f84710b436cbe0b32289d0838f4">tvm::te::var</a></div><div class="ttdeci">Var var(std::string name_hint, DataType t=DataType::Int(32))</div><div class="ttdoc">Construct a new Var expression. </div></div>
diff --git a/docs/reference/api/doxygen/dataflow__pattern_8h_source.html b/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
index c52622c09..ea7c755ac 100644
--- a/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
+++ b/docs/reference/api/doxygen/dataflow__pattern_8h_source.html
@@ -128,7 +128,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1relay_html_a3834130d66634d032f8e9bffafbe09ad"><div class="ttname"><a href="namespacetvm_1_1relay.html#a3834130d66634d032f8e9bffafbe09ad">tvm::relay::IsTuple</a></div><div class="ttdeci">DFPattern IsTuple(const Array< DFPattern > &fields)</div><div class="ttdoc">Syntatic Sugar for creating a TuplePattern. </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1FunctionPatternNode_html_a5e831242707df5d59474816c416abe97"><div class="ttname"><a href="classtvm_1_1relay_1_1FunctionPatternNode.html#a5e831242707df5d59474816c416abe97">tvm::relay::FunctionPatternNode::VisitAttrs</a></div><div class="ttdeci">void VisitAttrs(tvm::AttrVisitor *v)</div><div class="ttdef"><b>Definition:</b> dataflow_pattern.h:201</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1RelayExpr_html"><div class="ttname"><a href="classtvm_1_1RelayExpr.html">tvm::RelayExpr</a></div><div class="ttdoc">Managed reference to RelayExprNode. </div><div class="ttdef"><b>Definition:</b> expr.h:217</div></div>
<div class="ttc" id="classtvm_1_1relay_1_1ConstantPatternNode_html"><div class="ttname"><a href="classtvm_1_1relay_1_1ConstantPatternNode.html">tvm::relay::ConstantPatternNode</a></div><div class="ttdoc">Container for Constant. </div><div class="ttdef"><b>Definition:</b> dataflow_pattern.h:138</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
diff --git a/docs/reference/api/doxygen/detail_2broadcast_8h_source.html b/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
index ae805cab1..e821c006e 100644
--- a/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2broadcast_8h_source.html
@@ -77,7 +77,7 @@ $(function() {
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_ae8c7db788e840dc1c2ed1f365d5ea829"><div class="ttname"><a href="namespacetvm_1_1tir.html#ae8c7db788e840dc1c2ed1f365d5ea829">tvm::tir::IntImmNode</a></div><div class="ttdeci">tvm::IntImmNode IntImmNode</div><div class="ttdef"><b>Definition:</b> expr.h:49</div></div>
<div class="ttc" id="namespacetvm_1_1tir_html_aed3f57cf8d1c3546f075701898c5b70f"><div class="ttname"><a href="namespacetvm_1_1tir.html#aed3f57cf8d1c3546f075701898c5b70f">tvm::tir::make_zero</a></div><div class="ttdeci">PrimExpr make_zero(DataType t, Span span=Span())</div><div class="ttdoc">Make a const zero expr. </div><div class="ttdef"><b>Definition:</b> op.h:1129</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html">tvm::te::Tensor</a></div><div class="ttdoc">Tensor structure representing a possible input, or intermediate computation result. </div><div class="ttdef"><b>Definition:</b> tensor.h:102</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_ae9734c8e6324f9be27fce8d45d0aa6f4"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#ae9734c8e6324f9be27fce8d45d0aa6f4">tvm::runtime::Array::begin</a></div><div class="ttdeci">iterator begin() const</div><div class="ttdef"><b>Definition:</b> array.h:366</div></div>
diff --git a/docs/reference/api/doxygen/detail_2extern_8h_source.html b/docs/reference/api/doxygen/detail_2extern_8h_source.html
index dea2bf559..5af023bd1 100644
--- a/docs/reference/api/doxygen/detail_2extern_8h_source.html
+++ b/docs/reference/api/doxygen/detail_2extern_8h_source.html
@@ -74,7 +74,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html_aebad9f7235dd20af649fb5c2113797b8"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html#aebad9f7235dd20af649fb5c2113797b8">tvm::runtime::DataType::Handle</a></div><div class="ttdeci">static DataType Handle(int bits=64, int lanes=1)</div><div class="ttdoc">Construct a handle type. </div><div class="ttdef"><b>Definition:</b> data_type.h:188</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_a28f99e6dd767482765b854ee9fc71f2c"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#a28f99e6dd767482765b854ee9fc71f2c">tvm::tir::builtin::tvm_stack_make_array</a></div><div class="ttdeci">const Op & tvm_stack_make_array()</div><div class="ttdoc">Allocate a NDArray(DLTensor) on stack, return the handle. </div></div>
<div class="ttc" id="classtvm_1_1te_1_1ExternOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ExternOp.html">tvm::te::ExternOp</a></div><div class="ttdoc">Managed reference to ExternOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:460</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_1_1tir_1_1builtin_html_abd540cb73407771ecfb4f78722ce5a1b"><div class="ttname"><a href="namespacetvm_1_1tir_1_1builtin.html#abd540cb73407771ecfb4f78722ce5a1b">tvm::tir::builtin::tvm_stack_make_shape</a></div><div class="ttdeci">const Op & tvm_stack_make_shape()</div><div class="ttdoc">Allocate a shape tuple on stack, return the handle. </div></div>
<div class="ttc" id="namespacetvm_1_1te_html_ae0c71f84710b436cbe0b32289d0838f4"><div class="ttname"><a href="namespacetvm_1_1te.html#ae0c71f84710b436cbe0b32289d0838f4">tvm::te::var</a></div><div class="ttdeci">Var var(std::string name_hint, DataType t=DataType::Int(32))</div><div class="ttdoc">Construct a new Var expression. </div></div>
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
diff --git a/docs/reference/api/doxygen/device__api_8h_source.html b/docs/reference/api/doxygen/device__api_8h_source.html
index ad51f8fdb..5a38e0f50 100644
--- a/docs/reference/api/doxygen/device__api_8h_source.html
+++ b/docs/reference/api/doxygen/device__api_8h_source.html
@@ -94,7 +94,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619adff7742765a9f6f50973675bf34ad264"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619adff7742765a9f6f50973675bf34ad264">tvm::runtime::kMaxSharedMemoryPerBlock</a></div><div class="ttdef"><b>Definition:</b> device_api.h:42</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619a90ebfaf325917db841553c65ce2ae630"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619a90ebfaf325917db841553c65ce2ae630">tvm::runtime::kMaxClockRate</a></div><div class="ttdef"><b>Definition:</b> device_api.h:45</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619a100cda550bad77fbaf993566c022bdf9"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619a100cda550bad77fbaf993566c022bdf9">tvm::runtime::kDriverVersion</a></div><div class="ttdef"><b>Definition:</b> device_api.h:51</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619aa707ea3fd97e625364ad60daa89be2da"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619aa707ea3fd97e625364ad60daa89be2da">tvm::runtime::kWarpSize</a></div><div class="ttdef"><b>Definition:</b> device_api.h:41</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_html_a46fef1ca0ccc05473e9bb0a8c6b66619ad7ca96c2095b4670de00ee1d0ca79201"><div class="ttname"><a href="namespacetvm_1_1runtime.html#a46fef1ca0ccc05473e9bb0a8c6b66619ad7ca96c2095b4670de00ee1d0ca79201">tvm::runtime::kGcnArch</a></div><div class="ttdef"><b>Definition:</b> device_api.h:49</div></div>
diff --git a/docs/reference/api/doxygen/einsum_8h_source.html b/docs/reference/api/doxygen/einsum_8h_source.html
index d64da9e5a..a926921b0 100644
--- a/docs/reference/api/doxygen/einsum_8h_source.html
+++ b/docs/reference/api/doxygen/einsum_8h_source.html
@@ -88,7 +88,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a830eee18b651d35c1b5fc972f611fcec"><div class="ttname"><a href="namespacetvm_1_1topi.html#a830eee18b651d35c1b5fc972f611fcec">tvm::topi::GetCombinedDimsView</a></div><div class="ttdeci">void GetCombinedDimsView(const Tensor &op, int iop, char *labels, Array< PrimExpr > *newshape, Array< PrimExpr > *newstride)</div><div class="ttdoc">If any dimensions are combined, create a view that combines them. Shows in newshape and newstri [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a9a9498e3d8d11a6f68faa9c43f055646"><div class="ttname"><a href="namespacetvm_1_1topi.html#a9a9498e3d8d11a6f68faa9c43f055646">tvm::topi::ParseOperandSubscripts</a></div><div class="ttdeci">int ParseOperandSubscripts(const char *subscripts, int length, int ndim, int iop, char *op_labels, char *label_counts, int *min_label, int *max_label)</div><div class="ttdoc">Parse the subscripts for one operand into an output of &#39;ndim&#39; labe [...]
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_afb771a1ebb231df6e61e22ce933ba40d"><div class="ttname"><a href="namespacetvm_1_1topi.html#afb771a1ebb231df6e61e22ce933ba40d">tvm::topi::ParseEinsumInput</a></div><div class="ttdeci">std::tuple< std::string, std::string > ParseEinsumInput(std::string subscripts, const std::vector< Array< PrimExpr >> &operands)</div><div class="ttdoc">Parse the input subscripts into a vector of strings. </div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html">tvm::te::Tensor</a></div><div class="ttdoc">Tensor structure representing a possible input, or intermediate computation result. </div><div class="ttdef"><b>Definition:</b> tensor.h:102</div></div>
diff --git a/docs/reference/api/doxygen/elemwise_8h_source.html b/docs/reference/api/doxygen/elemwise_8h_source.html
index a0b4697db..944c6857b 100644
--- a/docs/reference/api/doxygen/elemwise_8h_source.html
+++ b/docs/reference/api/doxygen/elemwise_8h_source.html
@@ -110,7 +110,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a99f3fd2edfd74113c83bc9fb98e8aca1"><div class="ttname"><a href="namespacetvm_1_1topi.html#a99f3fd2edfd74113c83bc9fb98e8aca1">tvm::topi::bitwise_not</a></div><div class="ttdeci">Tensor bitwise_not(const Tensor &x, std::string name="T_bitwise_not", std::string tag=kElementWise)</div><div class="ttdoc">Creates an operation that returns the bitwise NOT of a given tensor. </div><div class="ttdef"><b>Definition:</b> elemwise.h:196</d [...]
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_aec153e599d33c78a7592007cde1c02cb"><div class="ttname"><a href="namespacetvm_1_1topi.html#aec153e599d33c78a7592007cde1c02cb">tvm::topi::tanh</a></div><div class="ttdeci">Tensor tanh(const Tensor &x, std::string name="T_" "tanh", std::string tag=kElementWise)</div><div class="ttdef"><b>Definition:</b> elemwise.h:73</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a188f69f0e65e2efb4914e458db50b3d8"><div class="ttname"><a href="namespacetvm_1_1topi.html#a188f69f0e65e2efb4914e458db50b3d8">tvm::topi::fast_erf_float32</a></div><div class="ttdeci">Tensor fast_erf_float32(const Tensor &data, std::string name, std::string tag)</div><div class="ttdoc">Fast_erf_float expression from Eigen. </div><div class="ttdef"><b>Definition:</b> elemwise.h:509</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a4435c7d12111817c485ebe9d2a6d608b"><div class="ttname"><a href="namespacetvm_1_1topi.html#a4435c7d12111817c485ebe9d2a6d608b">tvm::topi::fast_erf_float16</a></div><div class="ttdeci">Tensor fast_erf_float16(const Tensor &data, std::string name, std::string tag)</div><div class="ttdoc">Fast_erf_float expression from Eigen for float16. </div><div class="ttdef"><b>Definition:</b> elemwise.h:518</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a472208fa01448c0ed649bec218eed7f9"><div class="ttname"><a href="namespacetvm_1_1topi.html#a472208fa01448c0ed649bec218eed7f9">tvm::topi::acos</a></div><div class="ttdeci">Tensor acos(const Tensor &x, std::string name="T_" "acos", std::string tag=kElementWise)</div><div class="ttdef"><b>Definition:</b> elemwise.h:66</div></div>
diff --git a/docs/reference/api/doxygen/index__map_8h_source.html b/docs/reference/api/doxygen/index__map_8h_source.html
index d4c04d936..b94f8b40c 100644
--- a/docs/reference/api/doxygen/index__map_8h_source.html
+++ b/docs/reference/api/doxygen/index__map_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1IndexMap_html"><div class="ttname"><a href="classtvm_1_1tir_1_1IndexMap.html">tvm::tir::IndexMap</a></div><div class="ttdef"><b>Definition:</b> index_map.h:143</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1TypedPackedFunc_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1TypedPackedFunc.html">tvm::runtime::TypedPackedFunc</a></div><div class="ttdoc">Please refer to TypedPackedFunc<R(Args..)>. </div><div class="ttdef"><b>Definition:</b> packed_func.h:60</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="object_8h_html"><div class="ttname"><a href="object_8h.html">object.h</a></div><div class="ttdoc">A managed object in the TVM runtime. </div></div>
diff --git a/docs/reference/api/doxygen/memory__manager_8h_source.html b/docs/reference/api/doxygen/memory__manager_8h_source.html
index 215147598..463ac6e52 100644
--- a/docs/reference/api/doxygen/memory__manager_8h_source.html
+++ b/docs/reference/api/doxygen/memory__manager_8h_source.html
@@ -81,7 +81,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1StorageObj_html_ae787a0a25d67ff1952ac5e9eeb0d1a61"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1StorageObj.html#ae787a0a25d67ff1952ac5e9eeb0d1a61">tvm::runtime::vm::StorageObj::buffer</a></div><div class="ttdeci">Buffer buffer</div><div class="ttdoc">The index into the VM function table. </div><div class="ttdef"><b>Definition:</b> memory_manager.h:117</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1vm_1_1MemoryManager_html_aeaa1e35590fd9bcbceea389d3dc1c3c3"><div class="ttname"><a href="classtvm_1_1runtime_1_1vm_1_1MemoryManager.html#aeaa1e35590fd9bcbceea389d3dc1c3c3">tvm::runtime::vm::MemoryManager::GetAllocator</a></div><div class="ttdeci">static Allocator * GetAllocator(Device dev)</div><div class="ttdoc">Get an allocator given the context. </div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1vm_1_1Buffer_html_a99624b7e535aba1bf5131a5afc08c1c4"><div class="ttname"><a href="structtvm_1_1runtime_1_1vm_1_1Buffer.html#a99624b7e535aba1bf5131a5afc08c1c4">tvm::runtime::vm::Buffer::data</a></div><div class="ttdeci">void * data</div><div class="ttdoc">The pointer to the allocated block of memory. </div><div class="ttdef"><b>Definition:</b> memory_manager.h:43</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
<div class="ttc" id="object_8h_html"><div class="ttname"><a href="object_8h.html">object.h</a></div><div class="ttdoc">A managed object in the TVM runtime. </div></div>
diff --git a/docs/reference/api/doxygen/ndarray_8h_source.html b/docs/reference/api/doxygen/ndarray_8h_source.html
index e874962c1..08e9b6629 100644
--- a/docs/reference/api/doxygen/ndarray_8h_source.html
+++ b/docs/reference/api/doxygen/ndarray_8h_source.html
@@ -111,7 +111,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_ac261cdb80487fb29ac42b28678f8cbef"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#ac261cdb80487fb29ac42b28678f8cbef">tvm::runtime::ObjectRef::data_</a></div><div class="ttdeci">ObjectPtr< Object > data_</div><div class="ttdoc">Internal pointer that backs the reference. </div><div class="ttdef"><b>Definition:</b> object.h:574</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase_html_a1063a9d01075d5b7b0e8fa31d4d72e0b"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray_1_1ContainerBase.html#a1063a9d01075d5b7b0e8fa31d4d72e0b">tvm::runtime::NDArray::ContainerBase::dl_tensor</a></div><div class="ttdeci">DLTensor dl_tensor</div><div class="ttdoc">The corresponding dl_tensor field. </div><div class="ttdef"><b>Definition:</b> ndarray.h:272</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1NDArray_1_1Container_html_a56109cfc826b26172f084c3790144351"><div class="ttname"><a href="classtvm_1_1runtime_1_1NDArray_1_1Container.html#a56109cfc826b26172f084c3790144351">tvm::runtime::NDArray::Container::SetDeleter</a></div><div class="ttdeci">void SetDeleter(FDeleter deleter)</div><div class="ttdoc">Set the deleter field. </div><div class="ttdef"><b>Definition:</b> ndarray.h:323</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="c__runtime__api_8h_html_ace8007daffd9f2c6d954c24d870bfcc4"><div class="ttname"><a href="c__runtime__api_8h.html#ace8007daffd9f2c6d954c24d870bfcc4">tvm_index_t</a></div><div class="ttdeci">int64_t tvm_index_t</div><div class="ttdoc">type of array index. </div><div class="ttdef"><b>Definition:</b> c_runtime_api.h:81</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_aadbc0886ffa80162ff31eefd0431ba09"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#aadbc0886ffa80162ff31eefd0431ba09">tvm::runtime::ObjectRef::get</a></div><div class="ttdeci">const Object * get() const</div><div class="ttdef"><b>Definition:</b> object.h:546</div></div>
diff --git a/docs/reference/api/doxygen/nn_2softmax_8h_source.html b/docs/reference/api/doxygen/nn_2softmax_8h_source.html
index e45fc1615..efedd615c 100644
--- a/docs/reference/api/doxygen/nn_2softmax_8h_source.html
+++ b/docs/reference/api/doxygen/nn_2softmax_8h_source.html
@@ -66,7 +66,7 @@ $(function() {
<div class="title">softmax.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="nn_2softmax_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
+<a href="nn_2softmax_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or more [...]
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> autodiff.h:35</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Var_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Var.html">tvm::tir::Var</a></div><div class="ttdoc">a named variable in TIR </div><div class="ttdef"><b>Definition:</b> var.h:88</div></div>
<div class="ttc" id="reduction_8h_html"><div class="ttname"><a href="reduction_8h.html">reduction.h</a></div><div class="ttdoc">Reduction op constructors. </div></div>
@@ -74,7 +74,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_1_1nn_html_aa2cb22c64412c3eacb351c12b883333b"><div class="ttname"><a href="namespacetvm_1_1topi_1_1nn.html#aa2cb22c64412c3eacb351c12b883333b">tvm::topi::nn::softmax</a></div><div class="ttdeci">Tensor softmax(const Tensor &x, int axis=-1, std::string name="tensor", std::string tag="softmax_output")</div><div class="ttdoc">Softmax activation. </div><div class="ttdef"><b>Definition:</b> softmax.h:50</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_ad58b3ba5122294bd1eb045b5792c3976"><div class="ttname"><a href="namespacetvm_1_1topi.html#ad58b3ba5122294bd1eb045b5792c3976">tvm::topi::MakeReduceTargetShape</a></div><div class="ttdeci">Array< PrimExpr > MakeReduceTargetShape(const std::vector< int > &real_axis, const Tensor &data, bool keepdims, bool atleast1d)</div><div class="ttdoc">Calculate the target shape for a reduce op. </div><div class="ttdef"><b>Definition:</b [...]
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_aa026b914ee05f81b6c20130b8905f257"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#aa026b914ee05f81b6c20130b8905f257">tvm::runtime::Array::push_back</a></div><div class="ttdeci">void push_back(const T &item)</div><div class="ttdoc">push a new item to the back of the list </div><div class="ttdef"><b>Definition:</b> array.h:436</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_1_1nn_html_ac0e20b6b30ec8296c1f037866d3bf772"><div class="ttname"><a href="namespacetvm_1_1topi_1_1nn.html#ac0e20b6b30ec8296c1f037866d3bf772">tvm::topi::nn::log_softmax</a></div><div class="ttdeci">Tensor log_softmax(const Tensor &x, std::string name="tensor", std::string tag="log_softmax_output")</div><div class="ttdoc">Log softmax activation. </div><div class="ttdef"><b>Definition:</b> softmax.h:125</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_1_1nn_html_ac0e20b6b30ec8296c1f037866d3bf772"><div class="ttname"><a href="namespacetvm_1_1topi_1_1nn.html#ac0e20b6b30ec8296c1f037866d3bf772">tvm::topi::nn::log_softmax</a></div><div class="ttdeci">Tensor log_softmax(const Tensor &x, std::string name="tensor", std::string tag="log_softmax_output")</div><div class="ttdoc">Log softmax activation. </div><div class="ttdef"><b>Definition:</b> softmax.h:126</div></div>
<div class="ttc" id="classtvm_1_1Range_html"><div class="ttname"><a href="classtvm_1_1Range.html">tvm::Range</a></div><div class="ttdoc">Range constainer. </div><div class="ttdef"><b>Definition:</b> expr.h:496</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a38fe82b0db9eab041324da16e532baff"><div class="ttname"><a href="namespacetvm_1_1topi.html#a38fe82b0db9eab041324da16e532baff">tvm::topi::MaxOp</a></div><div class="ttdeci">PrimExpr MaxOp(PrimExpr source, Array< IterVar > axis, Array< PrimExpr > init={}, Span span=Span())</div><div class="ttdoc">Wrap tvm::max to ensure we get the correct overload. </div><div class="ttdef"><b>Definition:</b> reduction.h:302</div></div>
<div class="ttc" id="namespacetvm_html_afdad0c0329bd39949ba8d296cfb85d76"><div class="ttname"><a href="namespacetvm.html#afdad0c0329bd39949ba8d296cfb85d76">tvm::sum</a></div><div class="ttdeci">PrimExpr sum(PrimExpr source, Array< tir::IterVar > axis, Array< PrimExpr > init={}, Span span=Span())</div><div class="ttdoc">sum of of source expression over axis </div></div>
diff --git a/docs/reference/api/doxygen/operation_8h_source.html b/docs/reference/api/doxygen/operation_8h_source.html
index a5b633308..a150f727b 100644
--- a/docs/reference/api/doxygen/operation_8h_source.html
+++ b/docs/reference/api/doxygen/operation_8h_source.html
@@ -122,7 +122,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1te_1_1ExternOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ExternOp.html">tvm::te::ExternOp</a></div><div class="ttdoc">Managed reference to ExternOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:460</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1te_1_1TensorComputeOpNode_html_a81533c6957c82df59ef8d810ace1bed2"><div class="ttname"><a href="classtvm_1_1te_1_1TensorComputeOpNode.html#a81533c6957c82df59ef8d810ace1bed2">tvm::te::TensorComputeOpNode::inputs</a></div><div class="ttdeci">Array< Tensor > inputs</div><div class="ttdoc">input tensors of intrin </div><div class="ttdef"><b>Definition:</b> operation.h:281</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1te_1_1ScanOp_html"><div class="ttname"><a href="classtvm_1_1te_1_1ScanOp.html">tvm::te::ScanOp</a></div><div class="ttdoc">Managed reference to ScanOpNode. </div><div class="ttdef"><b>Definition:</b> operation.h:399</div></div>
<div class="ttc" id="classtvm_1_1te_1_1ScanOpNode_html_a1b681295f74cb94732ef167a15a8488f"><div class="ttname"><a href="classtvm_1_1te_1_1ScanOpNode.html#a1b681295f74cb94732ef167a15a8488f">tvm::te::ScanOpNode::ScanOpNode</a></div><div class="ttdeci">ScanOpNode()</div><div class="ttdoc">constructor </div><div class="ttdef"><b>Definition:</b> operation.h:360</div></div>
diff --git a/docs/reference/api/doxygen/profiling_8h_source.html b/docs/reference/api/doxygen/profiling_8h_source.html
index 4c12c9ed3..ab5286226 100644
--- a/docs/reference/api/doxygen/profiling_8h_source.html
+++ b/docs/reference/api/doxygen/profiling_8h_source.html
@@ -102,7 +102,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1profiling_1_1ReportNode_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1ReportNode.html">tvm::runtime::profiling::ReportNode</a></div><div class="ttdoc">Data collected from a profiling run. Includes per-call metrics and per-device metrics. </div><div class="ttdef"><b>Definition:</b> profiling.h:177</div></div>
<div class="ttc" id="device__api_8h_html"><div class="ttname"><a href="device__api_8h.html">device_api.h</a></div><div class="ttdoc">Abstract device memory management API. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_html_a7c2095aed90b2129ba631b90103313a2"><div class="ttname"><a href="namespacetvm.html#a7c2095aed90b2129ba631b90103313a2">tvm::Device</a></div><div class="ttdeci">DLDevice Device</div><div class="ttdef"><b>Definition:</b> ndarray.h:43</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1profiling_1_1Report_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1profiling_1_1Report.html">tvm::runtime::profiling::Report</a></div><div class="ttdef"><b>Definition:</b> profiling.h:253</div></div>
<div class="ttc" id="namespacetvm_1_1runtime_1_1profiling_html_a213f5d3fec6828976d6eaf847a9018e4"><div class="ttname"><a href="namespacetvm_1_1runtime_1_1profiling.html#a213f5d3fec6828976d6eaf847a9018e4">tvm::runtime::profiling::ProfileFunction</a></div><div class="ttdeci">PackedFunc ProfileFunction(Module mod, std::string func_name, int device_type, int device_id, int warmup_iters, Array< MetricCollector > collectors)</div><div class="ttdoc">Collect performance information of a fu [...]
diff --git a/docs/reference/api/doxygen/ravel__unravel_8h_source.html b/docs/reference/api/doxygen/ravel__unravel_8h_source.html
index 8ef073964..2202c68b5 100644
--- a/docs/reference/api/doxygen/ravel__unravel_8h_source.html
+++ b/docs/reference/api/doxygen/ravel__unravel_8h_source.html
@@ -70,7 +70,7 @@ $(function() {
<div class="ttc" id="namespacetvm_html"><div class="ttname"><a href="namespacetvm.html">tvm</a></div><div class="ttdoc">runtime implementation for LibTorch/TorchScript. </div><div class="ttdef"><b>Definition:</b> analyzer.h:36</div></div>
<div class="ttc" id="namespacetvm_1_1te_html"><div class="ttname"><a href="namespacetvm_1_1te.html">tvm::te</a></div><div class="ttdoc">Tensor expression language DSL. </div><div class="ttdef"><b>Definition:</b> autodiff.h:35</div></div>
<div class="ttc" id="namespacetvm_html_a8f30aa0685ca52f846843e76a1ad1dc7"><div class="ttname"><a href="namespacetvm.html#a8f30aa0685ca52f846843e76a1ad1dc7">tvm::indexdiv</a></div><div class="ttdeci">PrimExpr indexdiv(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute floor(a / b) where a and b are non-negative. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="operation_8h_html"><div class="ttname"><a href="operation_8h.html">operation.h</a></div><div class="ttdoc">Operation node can generate one or multiple Tensors. </div></div>
</div><!-- fragment --></div><!-- contents -->
<!-- start footer part -->
diff --git a/docs/reference/api/doxygen/shape__tuple_8h_source.html b/docs/reference/api/doxygen/shape__tuple_8h_source.html
index 218839933..07eeec69d 100644
--- a/docs/reference/api/doxygen/shape__tuple_8h_source.html
+++ b/docs/reference/api/doxygen/shape__tuple_8h_source.html
@@ -80,7 +80,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a6836ad757cbcac207ddf025a74ac2ef2"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a6836ad757cbcac207ddf025a74ac2ef2">tvm::runtime::ShapeTuple::ShapeTuple</a></div><div class="ttdeci">ShapeTuple(IterType begin, IterType end)</div><div class="ttdoc">Constructor from iterator. </div><div class="ttdef"><b>Definition:</b> shape_tuple.h:98</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a93afa6c6de6d38665b62a007892a8632"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a93afa6c6de6d38665b62a007892a8632">tvm::runtime::ShapeTuple::begin</a></div><div class="ttdeci">const index_type * begin() const</div><div class="ttdef"><b>Definition:</b> shape_tuple.h:158</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTuple_html_a7e4f6df331fcf589c3f5544c88931561"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTuple.html#a7e4f6df331fcf589c3f5544c88931561">tvm::runtime::ShapeTuple::empty</a></div><div class="ttdeci">bool empty() const</div><div class="ttdef"><b>Definition:</b> shape_tuple.h:149</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ShapeTupleObj_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ShapeTupleObj.html">tvm::runtime::ShapeTupleObj</a></div><div class="ttdoc">An object representing a shape tuple. </div><div class="ttdef"><b>Definition:</b> shape_tuple.h:36</div></div>
<div class="ttc" id="structtvm_1_1runtime_1_1TypeIndex_html_aed93c7318efc8052201d4c404b21a40dae2bdfcaf2a93d7e1dfef9012bd0cae77"><div class="ttname"><a href="structtvm_1_1runtime_1_1TypeIndex.html#aed93c7318efc8052201d4c404b21a40dae2bdfcaf2a93d7e1dfef9012bd0cae77">tvm::runtime::TypeIndex::kRuntimeShapeTuple</a></div><div class="ttdoc">runtime::ShapeTuple. </div><div class="ttdef"><b>Definition:</b> object.h:72</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
diff --git a/docs/reference/api/doxygen/tensor_8h_source.html b/docs/reference/api/doxygen/tensor_8h_source.html
index dda1d9902..caca1c425 100644
--- a/docs/reference/api/doxygen/tensor_8h_source.html
+++ b/docs/reference/api/doxygen/tensor_8h_source.html
@@ -95,7 +95,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
<div class="ttc" id="classtvm_1_1te_1_1TensorNode_html_a153569448cb1bf9d2924d35639c3b8b8"><div class="ttname"><a href="classtvm_1_1te_1_1TensorNode.html#a153569448cb1bf9d2924d35639c3b8b8">tvm::te::TensorNode::TensorNode</a></div><div class="ttdeci">TensorNode()</div><div class="ttdoc">constructor </div><div class="ttdef"><b>Definition:</b> tensor.h:79</div></div>
<div class="ttc" id="classtvm_1_1te_1_1Tensor_1_1Slice_html_a1a00e3ec5f80973c337b0e7ab9c0974d"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor_1_1Slice.html#a1a00e3ec5f80973c337b0e7ab9c0974d">tvm::te::Tensor::Slice::operator[]</a></div><div class="ttdeci">Slice operator[](PrimExpr i)</div><div class="ttdoc">get i-th slice from the current slice. </div><div class="ttdef"><b>Definition:</b> tensor.h:187</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_aadbc0886ffa80162ff31eefd0431ba09"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#aadbc0886ffa80162ff31eefd0431ba09">tvm::runtime::ObjectRef::get</a></div><div class="ttdeci">const Object * get() const</div><div class="ttdef"><b>Definition:</b> object.h:546</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html">tvm::runtime::ObjectRef</a></div><div class="ttdoc">Base class of all object reference. </div><div class="ttdef"><b>Definition:</b> object.h:511</div></div>
diff --git a/docs/reference/api/doxygen/tensor__type_8h_source.html b/docs/reference/api/doxygen/tensor__type_8h_source.html
index 5868b7877..d240cbe19 100644
--- a/docs/reference/api/doxygen/tensor__type_8h_source.html
+++ b/docs/reference/api/doxygen/tensor__type_8h_source.html
@@ -88,7 +88,7 @@ $(function() {
<div class="ttc" id="classtvm_1_1TensorTypeNode_html_a84759da6fdc0984edcc65a8dda484505"><div class="ttname"><a href="classtvm_1_1TensorTypeNode.html#a84759da6fdc0984edcc65a8dda484505">tvm::TensorTypeNode::SEqualReduce</a></div><div class="ttdeci">bool SEqualReduce(const TensorTypeNode *other, SEqualReducer equal) const</div><div class="ttdef"><b>Definition:</b> tensor_type.h:77</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html">tvm::runtime::Array</a></div><div class="ttdoc">Array, container representing a contiguous sequence of ObjectRefs. </div><div class="ttdef"><b>Definition:</b> array.h:270</div></div>
<div class="ttc" id="classtvm_1_1TypeNode_html"><div class="ttname"><a href="classtvm_1_1TypeNode.html">tvm::TypeNode</a></div><div class="ttdoc">Type is the base type of all types. </div><div class="ttdef"><b>Definition:</b> type.h:74</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="classtvm_1_1BaseTensorTypeNode_html_afc675db92c700532b65fe819b1a37eb5"><div class="ttname"><a href="classtvm_1_1BaseTensorTypeNode.html#afc675db92c700532b65fe819b1a37eb5">tvm::BaseTensorTypeNode::TVM_DECLARE_BASE_OBJECT_INFO</a></div><div class="ttdeci">TVM_DECLARE_BASE_OBJECT_INFO(BaseTensorTypeNode, TypeNode)</div></div>
<div class="ttc" id="object_8h_html_ac6e7295a4999e2c8e4a2c990beca887a"><div class="ttname"><a href="object_8h.html#ac6e7295a4999e2c8e4a2c990beca887a">TVM_DEFINE_OBJECT_REF_METHODS</a></div><div class="ttdeci">#define TVM_DEFINE_OBJECT_REF_METHODS(TypeName, ParentType, ObjectName)</div><div class="ttdef"><b>Definition:</b> object.h:713</div></div>
<div class="ttc" id="object_8h_html_a3aea9b3f65aeb9150c0fa7800e5573c6"><div class="ttname"><a href="object_8h.html#a3aea9b3f65aeb9150c0fa7800e5573c6">TVM_DECLARE_FINAL_OBJECT_INFO</a></div><div class="ttdeci">#define TVM_DECLARE_FINAL_OBJECT_INFO(TypeName, ParentType)</div><div class="ttdoc">helper macro to declare type information in a final class. </div><div class="ttdef"><b>Definition:</b> object.h:671</div></div>
diff --git a/docs/reference/api/doxygen/topi_2nn_8h_source.html b/docs/reference/api/doxygen/topi_2nn_8h_source.html
index b16ea2944..0fa9b01d4 100644
--- a/docs/reference/api/doxygen/topi_2nn_8h_source.html
+++ b/docs/reference/api/doxygen/topi_2nn_8h_source.html
@@ -102,7 +102,7 @@ $(function() {
<div class="ttc" id="namespacetvm_1_1topi_html_a0250c4095f19ae8a22ed85bc4ce5a40d"><div class="ttname"><a href="namespacetvm_1_1topi.html#a0250c4095f19ae8a22ed85bc4ce5a40d">tvm::topi::kElementWise</a></div><div class="ttdeci">constexpr auto kElementWise</div><div class="ttdef"><b>Definition:</b> tags.h:32</div></div>
<div class="ttc" id="namespacetvm_html_a8f30aa0685ca52f846843e76a1ad1dc7"><div class="ttname"><a href="namespacetvm.html#a8f30aa0685ca52f846843e76a1ad1dc7">tvm::indexdiv</a></div><div class="ttdeci">PrimExpr indexdiv(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute floor(a / b) where a and b are non-negative. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a786c950302117f8bdbbcab523f7b83bb"><div class="ttname"><a href="namespacetvm_1_1topi.html#a786c950302117f8bdbbcab523f7b83bb">tvm::topi::depthwise_conv2d_nchw</a></div><div class="ttdeci">tvm::te::Tensor depthwise_conv2d_nchw(const tvm::te::Tensor &I, const tvm::te::Tensor &W, int pad_h=0, int pad_w=0, int stride_h=1, int stride_w=1, std::string name="T_depthwise_conv2d_nchw", std::string tag=kDepthwiseConv2dNCHW)</div><div [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
<div class="ttc" id="namespacetvm_1_1te_html_aae384e9b73c2271905486e4a74b69265"><div class="ttname"><a href="namespacetvm_1_1te.html#aae384e9b73c2271905486e4a74b69265">tvm::te::reduce_axis</a></div><div class="ttdeci">IterVar reduce_axis(Range dom, std::string name="rv")</div><div class="ttdoc">Create a new IterVar for reduction operations. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a3305d377f96cd20c23032eeada2756d5"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3305d377f96cd20c23032eeada2756d5">tvm::topi::pad</a></div><div class="ttdeci">tvm::te::Tensor pad(const tvm::te::Tensor &t, const tvm::Array< tvm::PrimExpr > &pad_before, tvm::Array< tvm::PrimExpr > pad_after=tvm::Array< tvm::PrimExpr >(), PrimExpr pad_value=PrimExpr(), std::string name="T_pad", std::string tag=kElem [...]
<div class="ttc" id="namespacetvm_html_a27d5567b95675d383c4675fdcd85346c"><div class="ttname"><a href="namespacetvm.html#a27d5567b95675d383c4675fdcd85346c">tvm::logical_and</a></div><div class="ttdeci">PrimExpr logical_and(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">and </div></div>
diff --git a/docs/reference/api/doxygen/topi_2transform_8h_source.html b/docs/reference/api/doxygen/topi_2transform_8h_source.html
index f540bfbd1..fe0461fce 100644
--- a/docs/reference/api/doxygen/topi_2transform_8h_source.html
+++ b/docs/reference/api/doxygen/topi_2transform_8h_source.html
@@ -66,11 +66,11 @@ $(function() {
<div class="title">transform.h</div> </div>
</div><!--header-->
<div class="contents">
-<a href="topi_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
+<a href="topi_2transform_8h.html">Go to the documentation of this file.</a><div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">/*</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment"> * Licensed to the Apache Software Foundation (ASF) under one</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment"> * or [...]
<div class="ttc" id="namespacetvm_html_aac2abc149c1a47944c37b560181b15c0"><div class="ttname"><a href="namespacetvm.html#aac2abc149c1a47944c37b560181b15c0">tvm::min</a></div><div class="ttdeci">PrimExpr min(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take minimum of two values </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Layout_html_a35389f5ca857483ea65756bb2ceaa944"><div class="ttname"><a href="classtvm_1_1tir_1_1Layout.html#a35389f5ca857483ea65756bb2ceaa944">tvm::tir::Layout::Equals</a></div><div class="ttdeci">bool Equals(const Layout &rhs) const</div><div class="ttdoc">Whether the two layouts are equal. </div><div class="ttdef"><b>Definition:</b> data_layout.h:276</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_acd9415b24624edac4edec4802d275062"><div class="ttname"><a href="namespacetvm_1_1topi.html#acd9415b24624edac4edec4802d275062">tvm::topi::strided_slice_with_axes</a></div><div class="ttdeci">Tensor strided_slice_with_axes(const Tensor &x, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, std::string slice_mode="end", s [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a877e6fdffb6b6c051c29602ec6fe995c"><div class="ttname"><a href="namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c">tvm::topi::sparse_to_dense</a></div><div class="ttdeci">Tensor sparse_to_dense(const Tensor &sparse_indices, const Array< PrimExpr > &output_shape, const Tensor &sparse_values, const PrimExpr &default_value, const std::string name="T_sparse_to_dense", const std::string tag=kInjective)</d [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a877e6fdffb6b6c051c29602ec6fe995c"><div class="ttname"><a href="namespacetvm_1_1topi.html#a877e6fdffb6b6c051c29602ec6fe995c">tvm::topi::sparse_to_dense</a></div><div class="ttdeci">Tensor sparse_to_dense(const Tensor &sparse_indices, const Array< PrimExpr > &output_shape, const Tensor &sparse_values, const PrimExpr &default_value, const std::string name="T_sparse_to_dense", const std::string tag=kInjective)</d [...]
<div class="ttc" id="namespacetvm_html_ada5ad8338d3144221d8f16380e6c4855"><div class="ttname"><a href="namespacetvm.html#ada5ad8338d3144221d8f16380e6c4855">tvm::indexmod</a></div><div class="ttdeci">PrimExpr indexmod(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute the remainder floor(a / b) where a and b are non-negative. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_aff75b2e533b654909ca1bd9485ef4e6b"><div class="ttname"><a href="namespacetvm_1_1topi.html#aff75b2e533b654909ca1bd9485ef4e6b">tvm::topi::StridedSliceOutputShape</a></div><div class="ttdeci">Array< PrimExpr > StridedSliceOutputShape(const Array< PrimExpr > &ishape, const Array< Integer > &begin, const Array< Integer > &end, const Array< Integer > &strides, const Array< Integer > &axes, co [...]
<div class="ttc" id="namespacetvm_1_1tir_html_a1a071208bbbab6b220cf46f5cdccdd86"><div class="ttname"><a href="namespacetvm_1_1tir.html#a1a071208bbbab6b220cf46f5cdccdd86">tvm::tir::make_const</a></div><div class="ttdeci">PrimExpr make_const(DataType t, ValueType value, Span span=Span())</div><div class="ttdoc">Make a const value with certain data type. </div><div class="ttdef"><b>Definition:</b> op.h:1121</div></div>
@@ -82,21 +82,21 @@ $(function() {
<div class="ttc" id="namespacetvm_html_a5e4738caa6bcd0259af64b25e25dfd93"><div class="ttname"><a href="namespacetvm.html#a5e4738caa6bcd0259af64b25e25dfd93">tvm::ceil</a></div><div class="ttdeci">PrimExpr ceil(PrimExpr x, Span span=Span())</div><div class="ttdoc">Calculate ceil(x) </div></div>
<div class="ttc" id="classtvm_1_1tir_1_1Var_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Var.html">tvm::tir::Var</a></div><div class="ttdoc">a named variable in TIR </div><div class="ttdef"><b>Definition:</b> var.h:88</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_af011847b6e7f72f1bec25eee05c80590"><div class="ttname"><a href="namespacetvm_1_1topi.html#af011847b6e7f72f1bec25eee05c80590">tvm::topi::where</a></div><div class="ttdeci">Tensor where(const Tensor &condition, const Tensor &x, const Tensor &y, std::string name="T_where", std::string tag=kBroadcast)</div><div class="ttdoc">Return the elements, either from x or y, depending on the condition. </div><div class="ttdef"><b>Def [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a3cf4e56cbd8144b9029672b7c5ebd161"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3cf4e56cbd8144b9029672b7c5ebd161">tvm::topi::one_hot</a></div><div class="ttdeci">Tensor one_hot(const Tensor &indices, const PrimExpr on_value, const PrimExpr off_value, int depth, int axis, const DataType &dtype, Array< PrimExpr > oshape=Array< PrimExpr >(), const std::string name="T_one_hot", const std::string tag=kInje [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a3cf4e56cbd8144b9029672b7c5ebd161"><div class="ttname"><a href="namespacetvm_1_1topi.html#a3cf4e56cbd8144b9029672b7c5ebd161">tvm::topi::one_hot</a></div><div class="ttdeci">Tensor one_hot(const Tensor &indices, const PrimExpr on_value, const PrimExpr off_value, int depth, int axis, const DataType &dtype, Array< PrimExpr > oshape=Array< PrimExpr >(), const std::string name="T_one_hot", const std::string tag=kInje [...]
<div class="ttc" id="namespacetvm_html_a353217978feabae3575560bf1586885f"><div class="ttname"><a href="namespacetvm.html#a353217978feabae3575560bf1586885f">tvm::if_then_else</a></div><div class="ttdeci">PrimExpr if_then_else(PrimExpr cond, PrimExpr true_value, PrimExpr false_value, Span span=Span())</div><div class="ttdoc">Conditional expression. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_aead477c6c9d4f4589d22b8acff82040c"><div class="ttname"><a href="namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c">tvm::topi::matrix_set_diag</a></div><div class="ttdeci">Tensor matrix_set_diag(const Tensor &input, const Tensor &diagonal, int k1, int k2, bool super_diag_right_align, bool sub_diag_right_align, const std::string name="T_matrix_set_diag", const std::string tag=kInjective)</div><div class="ttdoc">Retu [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_aead477c6c9d4f4589d22b8acff82040c"><div class="ttname"><a href="namespacetvm_1_1topi.html#aead477c6c9d4f4589d22b8acff82040c">tvm::topi::matrix_set_diag</a></div><div class="ttdeci">Tensor matrix_set_diag(const Tensor &input, const Tensor &diagonal, int k1, int k2, bool super_diag_right_align, bool sub_diag_right_align, const std::string name="T_matrix_set_diag", const std::string tag=kInjective)</div><div class="ttdoc">Retu [...]
<div class="ttc" id="namespacetvm_1_1topi_html_aa9f70e7392653f38da6ff53f5f554f98"><div class="ttname"><a href="namespacetvm_1_1topi.html#aa9f70e7392653f38da6ff53f5f554f98">tvm::topi::kMatMul</a></div><div class="ttdeci">constexpr auto kMatMul</div><div class="ttdef"><b>Definition:</b> tags.h:37</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a29e22aa45900dad3b6f9f705bb1dc688"><div class="ttname"><a href="namespacetvm_1_1topi.html#a29e22aa45900dad3b6f9f705bb1dc688">tvm::topi::kInjective</a></div><div class="ttdeci">constexpr auto kInjective</div><div class="ttdef"><b>Definition:</b> tags.h:33</div></div>
<div class="ttc" id="classtvm_1_1arith_1_1Analyzer_html_a9b440f852f12ad0a4d8ed5ed97054425"><div class="ttname"><a href="classtvm_1_1arith_1_1Analyzer.html#a9b440f852f12ad0a4d8ed5ed97054425">tvm::arith::Analyzer::Simplify</a></div><div class="ttdeci">PrimExpr Simplify(const PrimExpr &expr, int steps=2)</div><div class="ttdoc">Simplify expr. </div></div>
<div class="ttc" id="strided__slice_8h_html"><div class="ttname"><a href="strided__slice_8h.html">strided_slice.h</a></div><div class="ttdoc">Utility functions for strided_slice op. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a8811a02532bbe3047986bf1a8449ac0e"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8811a02532bbe3047986bf1a8449ac0e">tvm::topi::unravel_index</a></div><div class="ttdeci">Tensor unravel_index(const Tensor &x, const Tensor &shape, std::string name="T_unravel", std::string tag=kInjective)</div><div class="ttdoc">Converts a flat index or array of flat indices into a tuple of coordinate arrays. ...</div><div class="ttde [...]
<div class="ttc" id="namespacetvm_1_1topi_html_af4e59b01a5842baf6b47ad3f83731f53"><div class="ttname"><a href="namespacetvm_1_1topi.html#af4e59b01a5842baf6b47ad3f83731f53">tvm::topi::split</a></div><div class="ttdeci">Array< Tensor > split(const Tensor &x, Array< PrimExpr > split_indices, int axis, std::string name="T_split", std::string tag=kInjective)</div><div class="ttdoc">Split a tensor into multiple sub-tensors. </div><div class="ttdef"><b>Definition:</b> [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a6fec3a88d419cd018cf1041cf3d99204"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6fec3a88d419cd018cf1041cf3d99204">tvm::topi::parse_auto_scheduler_layout</a></div><div class="ttdeci">void parse_auto_scheduler_layout(const String &layout, Array< PrimExpr > *shape, std::vector< std::string > *axes)</div><div class="ttdoc">Utility function for auto_scheduler_layout_transform. </div><div class="ttdef"><b>Definition:</b> [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a6fec3a88d419cd018cf1041cf3d99204"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6fec3a88d419cd018cf1041cf3d99204">tvm::topi::parse_auto_scheduler_layout</a></div><div class="ttdeci">void parse_auto_scheduler_layout(const String &layout, Array< PrimExpr > *shape, std::vector< std::string > *axes)</div><div class="ttdoc">Utility function for auto_scheduler_layout_transform. </div><div class="ttdef"><b>Definition:</b> [...]
<div class="ttc" id="namespacetvm_1_1topi_html_af392bc8e9dc0d34792652a4c0cf92243"><div class="ttname"><a href="namespacetvm_1_1topi.html#af392bc8e9dc0d34792652a4c0cf92243">tvm::topi::gather</a></div><div class="ttdeci">Tensor gather(const Tensor &data, int axis, const Tensor &indices, std::string name="T_gather", std::string tag=kInjective)</div><div class="ttdoc">Gather values along given axis from given indices. </div><div class="ttdef"><b>Definition:</b> transform.h: [...]
<div class="ttc" id="classtvm_1_1te_1_1Tensor_html_a7c8d978e9905bb0f0f88226d4f5cbe7a"><div class="ttname"><a href="classtvm_1_1te_1_1Tensor.html#a7c8d978e9905bb0f0f88226d4f5cbe7a">tvm::te::Tensor::ndim</a></div><div class="ttdeci">size_t ndim() const</div><div class="ttdef"><b>Definition:</b> tensor.h:214</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a5efc5887d91eb272e31c10f4e014a034"><div class="ttname"><a href="namespacetvm_1_1topi.html#a5efc5887d91eb272e31c10f4e014a034">tvm::topi::dyn_tile</a></div><div class="ttdeci">Tensor dyn_tile(const Tensor &x, Array< PrimExpr > new_shape, size_t rdim, std::string name="T_tile", std::string tag=kBroadcast)</div><div class="ttdoc">Creates an operation to tile elements of an array. </div><div class="ttdef"><b>Definition:</b> tr [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a8a41a08eee70607889b738946ed97873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8a41a08eee70607889b738946ed97873">tvm::topi::layout_transform</a></div><div class="ttdeci">Tensor layout_transform(const Tensor &src, const std::string &src_layout, const std::string &dst_layout, const std::string name="T_layout_trans", const std::string tag=kInjective)</div><div class="ttdoc">Transform the layout according to src [...]
-<div class="ttc" id="namespacetvm_1_1topi_html_a8e10f74deef4f22a9dc4b0a0b4370b08"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8e10f74deef4f22a9dc4b0a0b4370b08">tvm::topi::auto_scheduler_layout_transform</a></div><div class="ttdeci">Tensor auto_scheduler_layout_transform(const Tensor &src, const String &src_layout, const String &dst_layout, const String name="T_auto_scheduler_layout_trans", const String tag=kInjective)</div><div class="ttdoc">Transform th [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a8a41a08eee70607889b738946ed97873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8a41a08eee70607889b738946ed97873">tvm::topi::layout_transform</a></div><div class="ttdeci">Tensor layout_transform(const Tensor &src, const std::string &src_layout, const std::string &dst_layout, const std::string name="T_layout_trans", const std::string tag=kInjective)</div><div class="ttdoc">Transform the layout according to src [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a8e10f74deef4f22a9dc4b0a0b4370b08"><div class="ttname"><a href="namespacetvm_1_1topi.html#a8e10f74deef4f22a9dc4b0a0b4370b08">tvm::topi::auto_scheduler_layout_transform</a></div><div class="ttdeci">Tensor auto_scheduler_layout_transform(const Tensor &src, const String &src_layout, const String &dst_layout, const String name="T_auto_scheduler_layout_trans", const String tag=kInjective)</div><div class="ttdoc">Transform th [...]
<div class="ttc" id="namespacetvm_html_a4bfb789a86d95f6241b50fd26f269c28"><div class="ttname"><a href="namespacetvm.html#a4bfb789a86d95f6241b50fd26f269c28">tvm::cast</a></div><div class="ttdeci">PrimExpr cast(const DataType &t, PrimExpr value, Span span=Span())</div><div class="ttdoc">cast value to type. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a845e38c0f34017d45ec318935b6ddf17"><div class="ttname"><a href="namespacetvm_1_1topi.html#a845e38c0f34017d45ec318935b6ddf17">tvm::topi::squeeze</a></div><div class="ttdeci">Tensor squeeze(const Tensor &x, Array< Integer > axis, bool atleast1d=false, std::string name="T_squeeze", std::string tag=kInjective)</div><div class="ttdoc">Remove size 1 dimensions from the shape of a tensor. The removed dimensions must have a const [...]
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_ab5db2ee9a8be71931324dac552be24c4"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#ab5db2ee9a8be71931324dac552be24c4">tvm::runtime::Array::Set</a></div><div class="ttdeci">void Set(int64_t i, T value)</div><div class="ttdoc">set i-th element of the array. </div><div class="ttdef"><b>Definition:</b> array.h:567</div></div>
@@ -108,7 +108,7 @@ $(function() {
<div class="ttc" id="constant__utils_8h_html"><div class="ttname"><a href="constant__utils_8h.html">constant_utils.h</a></div><div class="ttdoc">Utility functions for handling constants in TVM expressions. </div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a13aaf23f0ab77f1ed4a7d4b7816bf210"><div class="ttname"><a href="namespacetvm_1_1topi.html#a13aaf23f0ab77f1ed4a7d4b7816bf210">tvm::topi::kBroadcast</a></div><div class="ttdeci">constexpr auto kBroadcast</div><div class="ttdef"><b>Definition:</b> tags.h:36</div></div>
<div class="ttc" id="classtvm_1_1Range_html"><div class="ttname"><a href="classtvm_1_1Range.html">tvm::Range</a></div><div class="ttdoc">Range constainer. </div><div class="ttdef"><b>Definition:</b> expr.h:496</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a1db52a53bfb38341ef89b375562731c6"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1db52a53bfb38341ef89b375562731c6">tvm::topi::arange</a></div><div class="ttdeci">Tensor arange(const PrimExpr &start, const PrimExpr &stop, const PrimExpr &step, DataType dtype, std::string name="T_arange", std::string tag=kInjective)</div><div class="ttdef"><b>Definition:</b> transform.h:1535</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a1db52a53bfb38341ef89b375562731c6"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1db52a53bfb38341ef89b375562731c6">tvm::topi::arange</a></div><div class="ttdeci">Tensor arange(const PrimExpr &start, const PrimExpr &stop, const PrimExpr &step, DataType dtype, std::string name="T_arange", std::string tag=kInjective)</div><div class="ttdef"><b>Definition:</b> transform.h:1538</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_aed6387e67d18b9d5ad18f510fd600a25"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#aed6387e67d18b9d5ad18f510fd600a25">tvm::runtime::Array::size</a></div><div class="ttdeci">size_t size() const</div><div class="ttdef"><b>Definition:</b> array.h:399</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1DataType_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1DataType.html">tvm::runtime::DataType</a></div><div class="ttdoc">Runtime primitive data type. </div><div class="ttdef"><b>Definition:</b> data_type.h:41</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1ObjectRef_html_a17d8d5ad92691f9e18e3e0ae8ef69e4f"><div class="ttname"><a href="classtvm_1_1runtime_1_1ObjectRef.html#a17d8d5ad92691f9e18e3e0ae8ef69e4f">tvm::runtime::ObjectRef::defined</a></div><div class="ttdeci">bool defined() const</div><div class="ttdef"><b>Definition:</b> object.h:544</div></div>
@@ -124,8 +124,8 @@ $(function() {
<div class="ttc" id="namespacetvm_html_a0df5ca82d2c566f628ebb2f1e84a3fcb"><div class="ttname"><a href="namespacetvm.html#a0df5ca82d2c566f628ebb2f1e84a3fcb">tvm::max</a></div><div class="ttdeci">PrimExpr max(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">take maximum of two values </div></div>
<div class="ttc" id="classtvm_1_1IntImmNode_html_a81f4c116ffb5931fdd64639eacad415d"><div class="ttname"><a href="classtvm_1_1IntImmNode.html#a81f4c116ffb5931fdd64639eacad415d">tvm::IntImmNode::value</a></div><div class="ttdeci">int64_t value</div><div class="ttdoc">the Internal value. </div><div class="ttdef"><b>Definition:</b> expr.h:277</div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1String_html"><div class="ttname"><a href="classtvm_1_1runtime_1_1String.html">tvm::runtime::String</a></div><div class="ttdoc">Reference to string objects. </div><div class="ttdef"><b>Definition:</b> string.h:129</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1701</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a453f9f5a35a9852a086ce0228ee22164"><div class="ttname"><a href="namespacetvm_1_1topi.html#a453f9f5a35a9852a086ce0228ee22164">tvm::topi::meshgrid</a></div><div class="ttdeci">Array< Tensor > meshgrid(const Array< Tensor > &inputs, const std::string &indexing, std::string name="T_meshgrid", std::string tag=kInjective)</div><div class="ttdoc">Produce grids by expanding input over dimensions defined by other inputs. [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_af30c02f3a3f37c7963b3af60fb9c72a1"><div class="ttname"><a href="namespacetvm_1_1topi.html#af30c02f3a3f37c7963b3af60fb9c72a1">tvm::topi::shape</a></div><div class="ttdeci">Tensor shape(const Tensor &src, DataType dtype, const std::string name="T_shape", const std::string tag=kInjective)</div><div class="ttdoc">Get the shape of input tensor. </div><div class="ttdef"><b>Definition:</b> transform.h:1704</div></div>
+<div class="ttc" id="namespacetvm_1_1topi_html_a453f9f5a35a9852a086ce0228ee22164"><div class="ttname"><a href="namespacetvm_1_1topi.html#a453f9f5a35a9852a086ce0228ee22164">tvm::topi::meshgrid</a></div><div class="ttdeci">Array< Tensor > meshgrid(const Array< Tensor > &inputs, const std::string &indexing, std::string name="T_meshgrid", std::string tag=kInjective)</div><div class="ttdoc">Produce grids by expanding input over dimensions defined by other inputs. [...]
<div class="ttc" id="namespacetvm_1_1te_html_aae384e9b73c2271905486e4a74b69265"><div class="ttname"><a href="namespacetvm_1_1te.html#aae384e9b73c2271905486e4a74b69265">tvm::te::reduce_axis</a></div><div class="ttdeci">IterVar reduce_axis(Range dom, std::string name="rv")</div><div class="ttdoc">Create a new IterVar for reduction operations. </div></div>
<div class="ttc" id="namespacetvm_html_a2428ea0e23bd9f7218aebd066bb2cd88"><div class="ttname"><a href="namespacetvm.html#a2428ea0e23bd9f7218aebd066bb2cd88">tvm::truncmod</a></div><div class="ttdeci">PrimExpr truncmod(PrimExpr a, PrimExpr b, Span span=Span())</div><div class="ttdoc">compute the remainder of truncdiv </div></div>
<div class="ttc" id="classtvm_1_1runtime_1_1Array_html_a6b097149e69ea03fe3b812a3f5f7fcd9"><div class="ttname"><a href="classtvm_1_1runtime_1_1Array.html#a6b097149e69ea03fe3b812a3f5f7fcd9">tvm::runtime::Array::end</a></div><div class="ttdeci">iterator end() const</div><div class="ttdef"><b>Definition:</b> array.h:369</div></div>
@@ -136,10 +136,10 @@ $(function() {
<div class="ttc" id="classtvm_1_1tir_1_1Select_html"><div class="ttname"><a href="classtvm_1_1tir_1_1Select.html">tvm::tir::Select</a></div><div class="ttdoc">Managed reference to SelectNode. </div><div class="ttdef"><b>Definition:</b> expr.h:589</div></div>
<div class="ttc" id="classtvm_1_1tir_1_1BijectiveLayout_html"><div class="ttname"><a href="classtvm_1_1tir_1_1BijectiveLayout.html">tvm::tir::BijectiveLayout</a></div><div class="ttdoc">Bijective function mapping for data layout transformation. Given two Layout, BijectiveLayout build an...</div><div class="ttdef"><b>Definition:</b> data_layout.h:330</div></div>
<div class="ttc" id="namespacetvm_1_1topi_html_a1488ee98fd053e8b01b481f720df77fa"><div class="ttname"><a href="namespacetvm_1_1topi.html#a1488ee98fd053e8b01b481f720df77fa">tvm::topi::transpose</a></div><div class="ttdeci">Tensor transpose(const Tensor &x, Array< Integer > axes, std::string name="T_transpose", std::string tag=kInjective)</div><div class="ttdoc">Permute the dimensions of an array. </div><div class="ttdef"><b>Definition:</b> transform.h:195</div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a92d2a9f409bae6731c5e5247de0b8c48"><div class="ttname"><a href="namespacetvm_1_1topi.html#a92d2a9f409bae6731c5e5247de0b8c48">tvm::topi::ndarray_size</a></div><div class="ttdeci">Tensor ndarray_size(const Tensor &src, const DataType &dtype, const std::string &name="ndarray_size", const std::string &tag=kInjective)</div><div class="ttdoc">Get the size of input tensor. </div><div class="ttdef"><b>Definition:</b> transf [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a92d2a9f409bae6731c5e5247de0b8c48"><div class="ttname"><a href="namespacetvm_1_1topi.html#a92d2a9f409bae6731c5e5247de0b8c48">tvm::topi::ndarray_size</a></div><div class="ttdeci">Tensor ndarray_size(const Tensor &src, const DataType &dtype, const std::string &name="ndarray_size", const std::string &tag=kInjective)</div><div class="ttdoc">Get the size of input tensor. </div><div class="ttdef"><b>Definition:</b> transf [...]
<div class="ttc" id="namespacetvm_1_1topi_html_a037a112cc5c556107797e36e7feb0873"><div class="ttname"><a href="namespacetvm_1_1topi.html#a037a112cc5c556107797e36e7feb0873">tvm::topi::sequence_mask</a></div><div class="ttdeci">Tensor sequence_mask(const Tensor &data, const Tensor &valid_length, double mask_value, int axis, std::string name="T_sequence_mask", std::string tag=kInjective)</div><div class="ttdoc">Mask the out-of-boundary elements of each sequence. </div><div [...]
<div class="ttc" id="namespacetvm_html_a0da40d3e210aa3b38a17982a7b7866b8"><div class="ttname"><a href="namespacetvm.html#a0da40d3e210aa3b38a17982a7b7866b8">tvm::ret</a></div><div class="ttdeci">PrimExpr ret(PrimExpr value, Span span=Span())</div><div class="ttdoc">Return the value. </div></div>
-<div class="ttc" id="namespacetvm_1_1topi_html_a6d9189f6ceb05cf0a309dbe3f2730b16"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6d9189f6ceb05cf0a309dbe3f2730b16">tvm::topi::adv_index</a></div><div class="ttdeci">Tensor adv_index(const Tensor &data, const Array< Tensor > &indices, const std::string name="advanced_index", const std::string tag=kInjective)</div><div class="ttdoc">Numpy style advanced indexing with tensor. </div><div class="ttdef"><b>Definit [...]
+<div class="ttc" id="namespacetvm_1_1topi_html_a6d9189f6ceb05cf0a309dbe3f2730b16"><div class="ttname"><a href="namespacetvm_1_1topi.html#a6d9189f6ceb05cf0a309dbe3f2730b16">tvm::topi::adv_index</a></div><div class="ttdeci">Tensor adv_index(const Tensor &data, const Array< Tensor > &indices, const std::string name="advanced_index", const std::string tag=kInjective)</div><div class="ttdoc">Numpy style advanced indexing with tensor. </div><div class="ttdef"><b>Definit [...]
<div class="ttc" id="tags_8h_html"><div class="ttname"><a href="tags_8h.html">tags.h</a></div><div class="ttdoc">External function interface to rocBLAS libraries. </div></div>
<div class="ttc" id="namespacetvm_1_1te_html_afe4f57aeb3dd5ae9c0b58135e14d67ca"><div class="ttname"><a href="namespacetvm_1_1te.html#afe4f57aeb3dd5ae9c0b58135e14d67ca">tvm::te::compute</a></div><div class="ttdeci">Tensor compute(Array< PrimExpr > shape, FCompute fcompute, std::string name="tensor", std::string tag="", Map< String, ObjectRef > attrs={})</div><div class="ttdoc">Construct a new tensor by computing over shape, using the computation rule: resul [...]
<div class="ttc" id="namespacetvm_1_1topi_html_ab8ad5eed3079de21c92a7639ed370096"><div class="ttname"><a href="namespacetvm_1_1topi.html#ab8ad5eed3079de21c92a7639ed370096">tvm::topi::reverse_sequence</a></div><div class="ttdeci">Tensor reverse_sequence(const Tensor &x, const Tensor &seq_lengths, int seq_axis=1, int batch_axis=0, std::string name="T_reverse_sequence", std::string tag=kInjective)</div><div class="ttdoc">Reverse the tensor for variable length slices. Input [...]
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 8719b9f83..f95adade6 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1157,7 +1157,7 @@ initialization order?).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.LocalBuilder">
-<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">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
+<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">LocalBuilder</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">timeout</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">15</span></span></em>, <em class="sig-param"><span class="n"><sp [...]
<dd><p>LocalBuilder use local CPU cores to build programs in parallel.</p>
<dl class="field-list simple">
<dt class="field-odd">Parameters</dt>
@@ -1715,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<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">
@@ -1752,7 +1752,7 @@ the initial naive schedule (state).</p>
<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>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index cf11a1e7c..44ec6b593 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/2389f1f0d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 0cb4ac0c7..91c02455b 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/2389f1f0d/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 734be3593..56a965431 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/2389f1f0d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 7dabc1547..3b0a2b42f 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/2389f1f0d/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 63e70ee26..0f7b556fe 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/2389f1f0d/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 734e9ed24..e1167541f 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/2389f1f0d/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 85838c2f7..ff2ebe4b6 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/2389f1f0d/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 7b9708ce1..42e2631c5 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/2389f1f0d/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/web/src/runtime.ts#L1134">runtime.ts:1134</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/2389f1f0d/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 96e842a35..e88f02292 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/2389f1f0d/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 7d33b3919..32347505c 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/2389f1f0d/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 19cbe18d8..0d9d566ba 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/2389f1f0d/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 b488c150c..3605191a5 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/2389f1f0d/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 d17a878d1..0e99741f2 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/2389f1f0d/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 018feeb87..4c2e42371 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/2389f1f0d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 e31b25020..980da219c 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/2389f1f0d/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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 270a2b2d5..c7a06e003 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/2389f1f0d/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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/2389f1f0d/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/2b0e082f3/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>
... 1458 lines suppressed ...