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 2022/04/24 09:22:23 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@822d863770f17d0aa2e37fb128438eb4b483d1f1)
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 54200881d deploying docs (apache/tvm@822d863770f17d0aa2e37fb128438eb4b483d1f1)
54200881d is described below
commit 54200881dad3f08974e8cab64fdff280509fd688
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Sun Apr 24 09:22:17 2022 +0000
deploying docs (apache/tvm@822d863770f17d0aa2e37fb128438eb4b483d1f1)
---
.../how_to/compile_models/from_darknet.rst.txt | 5 +
.../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 | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 4 +-
.../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 | 2703 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 78 +-
.../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 | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 6 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 55 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_darknet.html | 1 +
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 147 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 56 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 108 +-
docs/how_to/deploy_models/deploy_prequantized.html | 15 +-
.../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 | 35 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 4 +-
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 | 2703 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 78 +-
.../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 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 6 +-
docs/tutorial/autotvm_relay_x86.html | 166 +-
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 22 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
117 files changed, 5994 insertions(+), 1314 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_darknet.rst.txt b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
index d19d70d36..854fbd15f 100644
--- a/docs/_sources/how_to/compile_models/from_darknet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_darknet.rst.txt
@@ -285,6 +285,11 @@ The process is no different from other examples.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 5.135 seconds)
+
+
.. _sphx_glr_download_how_to_compile_models_from_darknet.py:
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 548202ccf..0115df78d 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.zip67880911-6b49-4538-938a-4b8f125626ab from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip0f941fee-8e3c-43fa-be3d-5d28049a2f8a 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 f674d0e8f..eef308240 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<08:23, 86.3kB/s]
0%| | 48.0k/41.5M [00:00<05:20, 135kB/s]
0%| | 104k/41.5M [00:00<03:28, 208kB/s]
0%| | 208k/41.5M [00:00<02:07, 339kB/s]
1%| | 288k/41.5M [00:00<01:38, 437kB/s]
1%| | 416k/41.5M [00:00<01:08, 633kB/s]
1%|1 | 528k/41.5M [00:01<00:57, 744kB/s]
2%|1 | 672k/41.5M [00:01<00:46, 911kB/s]
2%|1 | 792k/41.5M [00:01<00:44, 957kB/s]
2%|2 | 936k/41.5M [00:01<00:40, 1.06MB/s]
2%|2 | 1.03M/41.5M [00:01<00:40, 1.06MB/s]
3%|2 | 1.19M/41.5M [00:01<00:35, 1.19MB/s]
3%|3 | 1.31M/41.5M [00:01<00:35, 1.17MB/s]
4%|3 | 1.48M/41.5M [00:01<00:31, 1.31MB/s]
4%|3 | 1.61M/41.5M [00:01<00:32, 1.28MB/s]
5%|4 | 1.91M/41.5M [00:02<00:30, 1.38MB/s]
5%|5 | 2.23M/41.5M [00:02<00:24, 1.7
0MB/s]
6%|5 | 2.41M/41.5M [00:02<00:23, 1.72MB/s]
6%|6 | 2.58M/41.5M [00:02<00:27, 1.47MB/s]
7%|6 | 2.77M/41.5M [00:02<00:25, 1.57MB/s]
7%|7 | 2.92M/41.5M [00:02<00:26, 1.52MB/s]
8%|7 | 3.12M/41.5M [00:02<00:24, 1.66MB/s]
8%|7 | 3.29M/41.5M [00:03<00:24, 1.64MB/s]
9%|8 | 3.68M/41.5M [00:03<00:21, 1.81MB/s]
10%|9 | 4.09M/41.5M [00:03<00:20, 1.92MB/s]
11%|# | 4.52M/41.5M [00:03<00:19, 2.03MB/s]
12%|#1 | 4.96M/41.5M [00:03<00:16, 2.35MB/s]
13%|#2 | 5.23M/41.5M [00:03<00:17, 2.23MB/s]
13%|#3 | 5.45M/41.5M [00:04<00:17, 2.12MB/s]
14%|#4 | 5.92M/41.5M [00:04<00:14, 2.50MB/s]
15%|#4 | 6.21M/41.5M [00:04<00:14, 2.60MB/s]
16%|#5 | 6.47M/41.5M [00:04<00:16, 2.26MB/s]
16%|#6 | 6.74M/41.5M [00:04<00:15, 2.39MB/s]
17%|#6 | 6.98M/41.5M [00:04<00:15, 2.33MB/s]
18%|#7 |
7.30M/41.5M [00:04<00:14, 2.54MB/s]
18%|#8 | 7.55M/41.5M [00:04<00:14, 2.47MB/s]
19%|#8 | 7.88M/41.5M [00:05<00:13, 2.70MB/s]
20%|#9 | 8.14M/41.5M [00:05<00:13, 2.67MB/s]
20%|## | 8.46M/41.5M [00:05<00:12, 2.86MB/s]
21%|##1 | 8.74M/41.5M [00:05<00:12, 2.79MB/s]
22%|##1 | 9.09M/41.5M [00:05<00:11, 2.93MB/s]
23%|##2 | 9.37M/41.5M [00:05<00:12, 2.80MB/s]
23%|##3 | 9.73M/41.5M [00:05<00:10, 3.05MB/s]
24%|##4 | 10.0M/41.5M [00:05<00:11, 2.96MB/s]
25%|##5 | 10.4M/41.5M [00:05<00:10, 3.23MB/s]
26%|##5 | 10.7M/41.5M [00:06<00:10, 3.17MB/s]
27%|##6 | 11.1M/41.5M [00:06<00:09, 3.38MB/s]
28%|##7 | 11.5M/41.5M [00:06<00:09, 3.32MB/s]
29%|##8 | 11.9M/41.5M [00:06<00:08, 3.56MB/s]
29%|##9 | 12.2M/41.5M [00:06<00:08, 3.55MB/s]
31%|### | 12.7M/41.5M [00:06<00:08, 3.72MB/s]
31%|###1 | 13.0M/41.5M [00:06<00:08, 3.
66MB/s]
32%|###2 | 13.5M/41.5M [00:06<00:07, 3.85MB/s]
33%|###3 | 13.8M/41.5M [00:06<00:07, 3.75MB/s]
34%|###4 | 14.3M/41.5M [00:06<00:07, 4.00MB/s]
35%|###5 | 14.7M/41.5M [00:07<00:07, 3.88MB/s]
37%|###6 | 15.2M/41.5M [00:07<00:06, 4.22MB/s]
38%|###7 | 15.6M/41.5M [00:07<00:06, 4.14MB/s]
39%|###8 | 16.1M/41.5M [00:07<00:05, 4.51MB/s]
40%|###9 | 16.6M/41.5M [00:07<00:05, 4.38MB/s]
41%|####1 | 17.1M/41.5M [00:07<00:05, 4.69MB/s]
42%|####2 | 17.6M/41.5M [00:07<00:05, 4.58MB/s]
44%|####3 | 18.1M/41.5M [00:07<00:05, 4.80MB/s]
45%|####4 | 18.6M/41.5M [00:07<00:05, 4.58MB/s]
46%|####6 | 19.2M/41.5M [00:08<00:04, 4.97MB/s]
47%|####7 | 19.7M/41.5M [00:08<00:04, 4.96MB/s]
49%|####8 | 20.3M/41.5M [00:08<00:04, 5.38MB/s]
50%|##### | 20.8M/41.5M [00:08<00:04, 5.38MB/s]
52%|#####1 | 21.5M/41.5M [00:08<00:03, 5.81MB/s]
53%|#####3 |
22.1M/41.5M [00:08<00:03, 5.79MB/s]
55%|#####4 | 22.7M/41.5M [00:08<00:03, 6.08MB/s]
56%|#####6 | 23.3M/41.5M [00:08<00:03, 6.05MB/s]
58%|#####7 | 24.0M/41.5M [00:08<00:02, 6.29MB/s]
59%|#####9 | 24.6M/41.5M [00:09<00:02, 6.26MB/s]
61%|######1 | 25.3M/41.5M [00:09<00:02, 6.55MB/s]
63%|######2 | 26.0M/41.5M [00:09<00:02, 6.51MB/s]
64%|######4 | 26.8M/41.5M [00:09<00:02, 6.90MB/s]
66%|######6 | 27.4M/41.5M [00:09<00:02, 6.79MB/s]
68%|######8 | 28.2M/41.5M [00:09<00:01, 7.25MB/s]
70%|######9 | 28.9M/41.5M [00:09<00:01, 7.14MB/s]
72%|#######2 | 29.9M/41.5M [00:09<00:01, 8.09MB/s]
74%|#######3 | 30.7M/41.5M [00:09<00:01, 8.05MB/s]
76%|#######5 | 31.5M/41.5M [00:09<00:01, 8.18MB/s]
78%|#######7 | 32.3M/41.5M [00:10<00:01, 7.88MB/s]
80%|#######9 | 33.1M/41.5M [00:10<00:01, 7.88MB/s]
81%|########1 | 33.8M/41.5M [00:10<00:01, 7.53MB/s]
84%|########3 | 34.7M/41.5M [00:10<00:00, 7
.60MB/s]
86%|########5 | 35.5M/41.5M [00:10<00:00, 7.87MB/s]
87%|########7 | 36.3M/41.5M [00:10<00:00, 6.91MB/s]
91%|######### | 37.6M/41.5M [00:10<00:00, 8.30MB/s]
93%|#########2| 38.4M/41.5M [00:10<00:00, 8.34MB/s]
95%|#########4| 39.2M/41.5M [00:11<00:00, 6.81MB/s]
97%|#########7| 40.4M/41.5M [00:11<00:00, 8.06MB/s]
99%|#########9| 41.2M/41.5M [00:11<00:00, 8.05MB/s]
100%|##########| 41.5M/41.5M [00:11<00:00, 3.84MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:04, 89.8kB/s]
0%| | 48.0k/41.5M [00:00<05:05, 142kB/s]
0%| | 80.0k/41.5M [00:00<04:33, 159kB/s]
0%| | 152k/41.5M [00:00<02:50, 255kB/s]
1%| | 312k/41.5M [00:00<01:29, 485kB/s]
1%|1 | 632k/41.5M [00:01<00:46, 928kB/s]
2%|2 | 976k/41.5M [00:01<00:33, 1.25MB/s]
3%|3 | 1.30M/41.5M [00:01<00:28, 1.48MB/s]
4%|4 | 1.66M/41.5M [00:01<00:24, 1.67MB/s]
5%|4 | 2.05M/41.5M [00:01<00:22, 1.83MB/s]
6%|5 | 2.45M/41.5M [00:02<00:20, 1.97MB/s]
7%|6 | 2.87M/41.5M [00:02<00:19, 2.10MB/s]
8%|7 | 3.30M/41.5M [00:02<00:18, 2.22MB/s]
9%|9 | 3.77M/41.5M [00:02<00:16, 2.35MB/s]
10%|# | 4.26M/41.5M [00:02<00:15, 2.49MB/s]
11%|#1 | 4.77M/41.5M [00:02<00:14, 2.61MB/s]
13%|#2 | 5.29M/41.5M [00:03<00:
13, 2.73MB/s]
14%|#4 | 5.82M/41.5M [00:03<00:13, 2.82MB/s]
15%|#5 | 6.38M/41.5M [00:03<00:12, 2.94MB/s]
17%|#6 | 6.98M/41.5M [00:03<00:11, 3.08MB/s]
18%|#8 | 7.58M/41.5M [00:03<00:11, 3.18MB/s]
20%|#9 | 8.20M/41.5M [00:04<00:10, 3.29MB/s]
21%|##1 | 8.84M/41.5M [00:04<00:10, 3.41MB/s]
23%|##2 | 9.53M/41.5M [00:04<00:09, 3.57MB/s]
25%|##4 | 10.2M/41.5M [00:04<00:08, 3.97MB/s]
26%|##6 | 11.0M/41.5M [00:04<00:07, 4.04MB/s]
28%|##8 | 11.7M/41.5M [00:04<00:07, 4.16MB/s]
30%|### | 12.6M/41.5M [00:05<00:07, 4.31MB/s]
32%|###2 | 13.4M/41.5M [00:05<00:06, 4.48MB/s]
34%|###4 | 14.3M/41.5M [00:05<00:06, 4.68MB/s]
37%|###6 | 15.2M/41.5M [00:05<00:05, 5.38MB/s]
38%|###8 | 15.8M/41.5M [00:05<00:04, 5.40MB/s]
39%|###9 | 16.3M/41.5M [00:05<00:05, 4.62MB/s]
42%|####1 | 17.3M/41.5M [00:06<00:05, 4.92MB/s]
44%|####4
| 18.4M/41.5M [00:06<00:04, 5.34MB/s]
47%|####6 | 19.5M/41.5M [00:06<00:04, 5.70MB/s]
50%|####9 | 20.7M/41.5M [00:06<00:03, 6.00MB/s]
53%|#####2 | 21.8M/41.5M [00:06<00:03, 6.23MB/s]
56%|#####5 | 23.1M/41.5M [00:06<00:02, 6.47MB/s]
59%|#####8 | 24.4M/41.5M [00:07<00:02, 6.77MB/s]
62%|######2 | 25.7M/41.5M [00:07<00:02, 7.09MB/s]
65%|######5 | 27.2M/41.5M [00:07<00:01, 8.10MB/s]
69%|######9 | 28.7M/41.5M [00:07<00:01, 7.58MB/s]
73%|#######2 | 30.2M/41.5M [00:07<00:01, 7.98MB/s]
77%|#######6 | 31.8M/41.5M [00:08<00:01, 8.25MB/s]
80%|######## | 33.3M/41.5M [00:08<00:01, 8.44MB/s]
84%|########4 | 34.9M/41.5M [00:08<00:00, 8.56MB/s]
88%|########7 | 36.4M/41.5M [00:08<00:00, 8.66MB/s]
92%|#########1| 38.0M/41.5M [00:08<00:00, 8.73MB/s]
95%|#########5| 39.6M/41.5M [00:08<00:00, 8.77MB/s]
99%|#########9| 41.1M/41.5M [00:09<00:00, 8.79MB/s]
100%|##########| 41.5M/41.5M [00:09<00
:00, 4.74MB/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 02b9f91ff..14bd119cc 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.807 seconds)
+ **Total running time of the script:** ( 1 minutes 10.337 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 58514fbf7..dd5b45e7d 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]
1%|1 | 512k/44.7M [00:00<00:09, 4.97MB/s]
5%|4 | 2.04M/44.7M [00:00<00:03, 11.4MB/s]
9%|8 | 3.82M/44.7M [00:00<00:02, 14.7MB/s]
13%|#2 | 5.67M/44.7M [00:00<00:02, 16.5MB/s]
16%|#6 | 7.26M/44.7M [00:00<00:02, 14.0MB/s]
19%|#9 | 8.65M/44.7M [00:00<00:03, 11.9MB/s]
22%|##2 | 9.86M/44.7M [00:00<00:03, 10.7MB/s]
24%|##4 | 10.9M/44.7M [00:01<00:03, 10.1MB/s]
27%|##6 | 11.9M/44.7M [00:01<00:03, 10.0MB/s]
29%|##8 | 12.9M/44.7M [00:01<00:03, 9.61MB/s]
32%|###1 | 14.2M/44.7M [00:01<00:02, 10.7MB/s]
36%|###6 | 16.1M/44.7M [00:01<00:02, 13.1MB/s]
40%|#### | 17.9M/44.7M [00:01<00:02, 13.8MB/s]
43%|####3 | 19.2M/44.7M [00:01<00:02, 12.8MB/s]
46%|####6 | 20.7M/44.7M [00:01<00:01, 13.4MB/s]
49%|####9 | 22.0M/44.7M [00:01<00:01, 13.4MB/s]
52%|#####2 | 23.3M/44.7M [00:
01<00:01, 13.3MB/s]
55%|#####5 | 24.6M/44.7M [00:02<00:01, 12.1MB/s]
58%|#####7 | 25.8M/44.7M [00:02<00:01, 10.6MB/s]
60%|###### | 26.9M/44.7M [00:02<00:01, 11.0MB/s]
63%|######3 | 28.3M/44.7M [00:02<00:01, 11.8MB/s]
66%|######6 | 29.5M/44.7M [00:02<00:01, 10.8MB/s]
68%|######8 | 30.5M/44.7M [00:02<00:01, 8.73MB/s]
71%|####### | 31.6M/44.7M [00:02<00:01, 9.15MB/s]
73%|#######2 | 32.5M/44.7M [00:03<00:01, 9.05MB/s]
76%|#######5 | 33.8M/44.7M [00:03<00:01, 9.97MB/s]
78%|#######8 | 35.0M/44.7M [00:03<00:00, 10.4MB/s]
81%|######## | 36.0M/44.7M [00:03<00:00, 10.1MB/s]
84%|########3 | 37.5M/44.7M [00:03<00:00, 11.3MB/s]
88%|########8 | 39.3M/44.7M [00:03<00:00, 12.1MB/s]
91%|######### | 40.5M/44.7M [00:03<00:00, 10.3MB/s]
93%|#########3| 41.6M/44.7M [00:03<00:00, 10.5MB/s]
96%|#########5| 42.7M/44.7M [00:04<00:00, 9.42MB/s]
99%|#########8| 44.1M/44.7M [00:04<00:00, 9.00MB/s]
100%
|##########| 44.7M/44.7M [00:04<00:00, 11.0MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
6%|6 | 2.69M/44.7M [00:00<00:01, 27.6MB/s]
12%|#1 | 5.33M/44.7M [00:00<00:01, 27.3MB/s]
18%|#7 | 7.94M/44.7M [00:00<00:02, 15.0MB/s]
22%|##1 | 9.78M/44.7M [00:00<00:02, 14.5MB/s]
26%|##5 | 11.4M/44.7M [00:00<00:02, 14.9MB/s]
31%|### | 13.8M/44.7M [00:00<00:01, 17.6MB/s]
35%|###5 | 15.7M/44.7M [00:00<00:01, 16.7MB/s]
39%|###8 | 17.4M/44.7M [00:01<00:01, 15.5MB/s]
44%|####3 | 19.5M/44.7M [00:01<00:01, 16.9MB/s]
47%|####7 | 21.2M/44.7M [00:01<00:01, 16.4MB/s]
53%|#####2 | 23.5M/44.7M [00:01<00:01, 18.4MB/s]
58%|#####8 | 25.9M/44.7M [00:01<00:00, 20.3MB/s]
64%|######3 | 28.4M/44.7M [00:01<00:00, 21.9MB/s]
68%|######8 | 30.5M/44.7M [00:01<00:00, 22.0MB/s]
74%|#######3 | 32.9M/44.7M [00:01<00:00, 22.6MB/s]
78%|#######8 | 35.0M/44.7M [00:01<00:00, 22.0MB/s]
83%|########3 | 37.2M/44.7M [00
:02<00:00, 20.3MB/s]
89%|########8 | 39.6M/44.7M [00:02<00:00, 21.8MB/s]
93%|#########3| 41.7M/44.7M [00:02<00:00, 19.7MB/s]
98%|#########7| 43.7M/44.7M [00:02<00:00, 18.0MB/s]
100%|##########| 44.7M/44.7M [00:02<00:00, 18.5MB/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 914fc5cba..ce941cbe7 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.238 seconds)
+ **Total running time of the script:** ( 1 minutes 1.916 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 662e8dd4c..99deed877 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
=================
-**05:32.910** total execution time for **how_to_compile_models** files:
+**05:34.448** total execution time for **how_to_compile_models** files:
-- **01:11.807**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:03.238**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:55.430**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:35.096**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:25.403**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.619**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:21.671**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.390**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:13.578**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.679**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **01:10.337**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:05.135**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **01:01.916**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:32.853**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **00:25.305**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:20.863**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:20.822**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:20.801**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.646**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.769**: :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 e810c132e..524c8f91d 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
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5388 15.5206 15.6660 15.4596 0.0746
+ 16.3223 16.5146 17.0414 15.5324 0.5463
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 779756820..e4dc82794 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]
1%| | 0.99M/170M [00:00<00:17, 9.93MB/s]
1%|1 | 2.41M/170M [00:00<00:13, 12.7MB/s]
2%|2 | 3.63M/170M [00:00<00:16, 10.8MB/s]
3%|3 | 5.10M/170M [00:00<00:14, 12.2MB/s]
4%|3 | 6.29M/170M [00:00<00:15, 11.4MB/s]
5%|4 | 8.35M/170M [00:00<00:11, 14.4MB/s]
6%|6 | 10.6M/170M [00:00<00:09, 17.2MB/s]
7%|7 | 12.3M/170M [00:00<00:10, 16.0MB/s]
8%|8 | 13.9M/170M [00:01<00:11, 14.6MB/s]
9%|9 | 15.3M/170M [00:01<00:11, 14.0MB/s]
10%|9 | 16.7M/170M [00:01<00:13, 11.9MB/s]
11%|# | 18.4M/170M [00:01<00:12, 13.2MB/s]
13%|#3 | 22.3M/170M [00:01<00:07, 20.1MB/s]
14%|#4 | 24.4M/170M [00:01<00:07, 20.5MB/s]
16%|#5 | 26.4M/170M [00:01<00:08, 17.7MB/s]
17%|#6 | 28.3M/170M [00:01<00:08, 17.2MB/s]
18%|#7 | 30.1M/170M [00:02<00:09, 16.3MB/
s]
19%|#8 | 32.1M/170M [00:02<00:08, 17.4MB/s]
20%|#9 | 33.8M/170M [00:02<00:09, 14.7MB/s]
21%|## | 35.3M/170M [00:02<00:11, 12.8MB/s]
22%|##1 | 36.6M/170M [00:02<00:11, 12.5MB/s]
22%|##2 | 37.9M/170M [00:02<00:11, 11.7MB/s]
23%|##3 | 39.5M/170M [00:02<00:10, 12.9MB/s]
24%|##4 | 41.3M/170M [00:02<00:09, 14.3MB/s]
25%|##5 | 42.8M/170M [00:03<00:10, 12.7MB/s]
26%|##6 | 44.5M/170M [00:03<00:09, 14.0MB/s]
27%|##7 | 45.9M/170M [00:03<00:09, 13.6MB/s]
28%|##8 | 47.7M/170M [00:03<00:08, 14.9MB/s]
29%|##9 | 49.5M/170M [00:03<00:07, 15.8MB/s]
30%|### | 51.1M/170M [00:03<00:08, 15.0MB/s]
31%|### | 52.5M/170M [00:03<00:08, 15.1MB/s]
32%|###1 | 54.1M/170M [00:03<00:07, 15.3MB/s]
33%|###2 | 55.6M/170M [00:03<00:07, 15.6MB/s]
34%|###3 | 57.2M/170M [00:04<00:07, 15.1MB/s]
35%|###4 | 59.1M/170M [00:04<00:
07, 16.3MB/s]
36%|###6 | 61.2M/170M [00:04<00:06, 17.6MB/s]
37%|###7 | 62.9M/170M [00:04<00:06, 16.0MB/s]
38%|###7 | 64.5M/170M [00:04<00:07, 14.5MB/s]
39%|###9 | 67.0M/170M [00:04<00:06, 17.5MB/s]
41%|#### | 69.0M/170M [00:04<00:05, 18.2MB/s]
42%|####2 | 71.6M/170M [00:04<00:04, 20.7MB/s]
43%|####3 | 73.7M/170M [00:05<00:05, 19.7MB/s]
45%|####4 | 75.6M/170M [00:05<00:05, 16.8MB/s]
46%|####6 | 78.2M/170M [00:05<00:04, 19.5MB/s]
47%|####7 | 80.2M/170M [00:05<00:04, 18.9MB/s]
48%|####8 | 82.1M/170M [00:05<00:05, 18.1MB/s]
49%|####9 | 83.9M/170M [00:05<00:05, 18.0MB/s]
50%|##### | 85.7M/170M [00:05<00:05, 15.7MB/s]
51%|#####1 | 87.2M/170M [00:05<00:05, 15.1MB/s]
52%|#####2 | 88.7M/170M [00:06<00:06, 13.6MB/s]
53%|#####3 | 90.1M/170M [00:06<00:06, 13.6MB/s]
54%|#####3 | 91.7M/170M [00:06<00:05, 14.3MB/s]
55%|#####4 | 93.1M/170M
[00:06<00:05, 13.6MB/s]
56%|#####5 | 94.8M/170M [00:06<00:05, 14.6MB/s]
57%|#####6 | 96.5M/170M [00:06<00:04, 15.4MB/s]
58%|#####7 | 98.3M/170M [00:06<00:04, 16.2MB/s]
59%|#####8 | 99.9M/170M [00:06<00:05, 14.2MB/s]
60%|#####9 | 102M/170M [00:06<00:04, 15.7MB/s]
61%|###### | 103M/170M [00:07<00:05, 12.7MB/s]
62%|######2 | 105M/170M [00:07<00:04, 14.4MB/s]
63%|######2 | 107M/170M [00:07<00:05, 12.5MB/s]
64%|######4 | 109M/170M [00:07<00:04, 14.3MB/s]
65%|######4 | 110M/170M [00:07<00:04, 14.4MB/s]
66%|######6 | 112M/170M [00:07<00:03, 15.8MB/s]
67%|######7 | 114M/170M [00:07<00:03, 16.0MB/s]
68%|######8 | 116M/170M [00:07<00:03, 16.5MB/s]
69%|######9 | 117M/170M [00:08<00:03, 15.3MB/s]
70%|######9 | 119M/170M [00:08<00:03, 15.6MB/s]
71%|####### | 120M/170M [00:08<00:03, 15.6MB/s]
72%|#######1 | 122M/170M [00:08<00:03, 15.9MB/s]
73%|#######2 | 124M/170M [
00:08<00:03, 16.1MB/s]
74%|#######4 | 126M/170M [00:08<00:02, 17.2MB/s]
75%|#######5 | 127M/170M [00:08<00:02, 15.0MB/s]
76%|#######5 | 129M/170M [00:08<00:02, 15.2MB/s]
77%|#######6 | 130M/170M [00:09<00:03, 11.3MB/s]
78%|#######7 | 132M/170M [00:09<00:03, 12.5MB/s]
79%|#######8 | 134M/170M [00:09<00:02, 14.5MB/s]
80%|######## | 136M/170M [00:09<00:02, 16.0MB/s]
81%|########1 | 138M/170M [00:09<00:02, 15.5MB/s]
82%|########2 | 140M/170M [00:09<00:01, 16.9MB/s]
83%|########3 | 142M/170M [00:09<00:01, 15.6MB/s]
84%|########4 | 143M/170M [00:09<00:01, 15.6MB/s]
85%|########5 | 145M/170M [00:10<00:02, 13.0MB/s]
87%|########6 | 147M/170M [00:10<00:01, 15.8MB/s]
88%|########7 | 149M/170M [00:10<00:01, 17.1MB/s]
89%|########8 | 151M/170M [00:10<00:01, 13.0MB/s]
90%|########9 | 152M/170M [00:10<00:01, 14.2MB/s]
91%|######### | 154M/170M [00:10<00:01, 15.2MB/s]
92%|#########1| 156M/170M [00:10<0
0:01, 13.7MB/s]
93%|#########2| 158M/170M [00:10<00:00, 14.7MB/s]
94%|#########3| 159M/170M [00:11<00:00, 13.5MB/s]
95%|#########5| 162M/170M [00:11<00:00, 16.3MB/s]
97%|#########6| 164M/170M [00:11<00:00, 19.4MB/s]
98%|#########8| 167M/170M [00:11<00:00, 21.5MB/s]
100%|#########9| 169M/170M [00:11<00:00, 20.4MB/s]
100%|##########| 170M/170M [00:11<00:00, 15.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
7%|6 | 11.2M/170M [00:00<00:01, 117MB/s]
16%|#6 | 27.7M/170M [00:00<00:00, 150MB/s]
28%|##7 | 47.3M/170M [00:00<00:00, 176MB/s]
39%|###9 | 66.7M/170M [00:00<00:00, 186MB/s]
50%|##### | 85.2M/170M [00:00<00:00, 189MB/s]
61%|###### | 103M/170M [00:00<00:00, 188MB/s]
71%|#######1 | 121M/170M [00:00<00:00, 184MB/s]
83%|########2 | 140M/170M [00:00<00:00, 189MB/s]
95%|#########4| 161M/170M [00:00<00:00, 198MB/s]
100%|##########| 170M/170M [00:00<00:00, 188MB/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').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 9.500 seconds)
+ **Total running time of the script:** ( 3 minutes 2.258 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 5621f9b4d..eebff22c6 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]
7%|7 | 1.01M/13.6M [00:00<00:01, 10.3MB/s]
16%|#6 | 2.19M/13.6M [00:00<00:01, 11.4MB/s]
28%|##8 | 3.85M/13.6M [00:00<00:00, 14.1MB/s]
38%|###8 | 5.20M/13.6M [00:00<00:00, 10.7MB/s]
50%|####9 | 6.75M/13.6M [00:00<00:00, 11.7MB/s]
59%|#####8 | 7.94M/13.6M [00:00<00:00, 11.3MB/s]
71%|####### | 9.59M/13.6M [00:00<00:00, 12.9MB/s]
80%|######## | 10.9M/13.6M [00:00<00:00, 11.8MB/s]
89%|########9 | 12.1M/13.6M [00:01<00:00, 12.0MB/s]
100%|##########| 13.6M/13.6M [00:01<00:00, 12.2MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 166MB/s]
@@ -344,7 +344,7 @@ 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)
- 90.0302 89.9670 91.2822 89.8079 0.2209
+ 90.4680 90.1832 97.7253 90.0221 1.0371
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.515 seconds)
+ **Total running time of the script:** ( 1 minutes 4.301 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 96dd99671..7a7ea402d 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
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.0240 117.8995 122.2729 116.1341 0.9010
+ 120.0440 120.0160 121.2119 119.2960 0.3302
@@ -385,7 +385,7 @@ 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 52.119 seconds)
+ **Total running time of the script:** ( 1 minutes 53.165 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 49b5032b5..f81568d11 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 36.736 seconds)
+ **Total running time of the script:** ( 1 minutes 11.472 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 39390777e..33c145259 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]
5%|4 | 6368/132723 [00:00<00:01, 63672.32KB/s]
11%|#1 | 14897/132723 [00:00<00:01, 76385.98KB/s]
18%|#7 | 23479/132723 [00:00<00:01, 80689.22KB/s]
24%|##4 | 32087/132723 [00:00<00:01, 82814.23KB/s]
31%|### | 40770/132723 [00:00<00:01, 84259.53KB/s]
37%|###7 | 49384/132723 [00:00<00:00, 84894.82KB/s]
44%|####3 | 57945/132723 [00:00<00:00, 85125.32KB/s]
50%|##### | 66458/132723 [00:00<00:00, 71183.84KB/s]
56%|#####5 | 73939/132723 [00:01<00:00, 60487.81KB/s]
61%|###### | 80456/132723 [00:01<00:00, 60996.03KB/s]
67%|######6 | 88391/132723 [00:01<00:00, 65757.99KB/s]
73%|#######3 | 96963/132723 [00:01<00:00, 71150.09KB/s]
80%|#######9 | 105644/132723 [00:01<00:00, 75512.47KB/s]
86%|########6 | 114291/132723 [00:01<00:00, 78627.39KB/s]
93%|#########2| 122937/132723 [00:01<00:00, 80888.66KB/s]
99%|########
#9| 131597/132723 [00:01<00:00, 82556.80KB/s]
100%|##########| 132723/132723 [00:01<00:00, 75800.40KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 7038/132723 [00:00<00:01, 70372.85KB/s]
12%|#1 | 15728/132723 [00:00<00:01, 80087.83KB/s]
18%|#8 | 24457/132723 [00:00<00:01, 83372.68KB/s]
25%|##5 | 33229/132723 [00:00<00:01, 85082.70KB/s]
32%|###1 | 41964/132723 [00:00<00:01, 85896.06KB/s]
38%|###8 | 50713/132723 [00:00<00:00, 86435.80KB/s]
45%|####4 | 59409/132723 [00:00<00:00, 86605.17KB/s]
51%|#####1 | 68157/132723 [00:00<00:00, 86880.58KB/s]
58%|#####7 | 76879/132723 [00:00<00:00, 86983.59KB/s]
65%|######4 | 85619/132723 [00:01<00:00, 87109.21KB/s]
71%|#######1 | 94397/132723 [00:01<00:00, 87310.19KB/s]
78%|#######7 | 103170/132723 [00:01<00:00, 87434.62KB/s]
84%|########4 | 111917/132723 [00:01<00:00, 87442.77KB/s]
91%|######### | 120662/132723 [00:01<00:00, 87398.53KB/s]
97%|#########7| 129402/132723 [00:01<00:00, 83114.54KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84019.88KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 19.867 seconds)
+ **Total running time of the script:** ( 2 minutes 20.377 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 d48b95680..a611252ab 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
=================
-**10:52.604** total execution time for **how_to_deploy_models** files:
+**10:20.622** total execution time for **how_to_deploy_models** files:
-- **03:09.500**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:19.867**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:52.119**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:36.736**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:04.515**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.540**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:21.137**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.190**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:02.258**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:20.377**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:53.165**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:11.472**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:04.301**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:27.587**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:21.262**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.199**: :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 f48dd01b2..1de053f92 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
@@ -423,7 +423,7 @@ 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.zipebb22811-12a9-49a8-a8d7-800ae10725cb from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip3f62893c-5c0e-48cc-a767-86f9621823b2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
@@ -525,7 +525,7 @@ Now, to actually convert the entire network, we have written `a pass in Relay <h
.. code-block:: none
- Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+ Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index 08f61fd83..2754d02ab 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
=================
-**00:39.769** total execution time for **how_to_extend_tvm** files:
+**00:37.938** total execution time for **how_to_extend_tvm** files:
-- **00:36.149**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.336**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.084**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.480**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.227**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.032**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.199**: :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 d4fb58b2e..a79af0362 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: 6301us [6301us] (45.44%; 45.44%)
- FoldScaleAxis: 7566us [2us] (54.56%; 54.56%)
- FoldConstant: 7564us [1556us] (54.55%; 99.97%)
- InferType: 6008us [6008us] (43.33%; 79.43%)
+ InferType: 6000us [6000us] (45.43%; 45.43%)
+ FoldScaleAxis: 7207us [2us] (54.57%; 54.57%)
+ FoldConstant: 7205us [1490us] (54.56%; 99.97%)
+ InferType: 5716us [5716us] (43.28%; 79.33%)
@@ -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: 6063us [6063us] (44.71%; 44.71%)
- FoldScaleAxis: 7497us [2us] (55.29%; 55.29%)
- FoldConstant: 7495us [1531us] (55.27%; 99.97%)
- InferType: 5964us [5964us] (43.98%; 79.57%)
+ InferType: 6149us [6149us] (45.55%; 45.55%)
+ FoldScaleAxis: 7351us [2us] (54.45%; 54.45%)
+ FoldConstant: 7349us [1585us] (54.44%; 99.97%)
+ InferType: 5764us [5764us] (42.70%; 78.43%)
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 48ad89a57..532d5fb5d 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: 47.082751 ms
+ Convolution: 38.570183 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 de8f97adf..221b3ea40 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: 6.855349 ms
+ conv2d with tensor core: 9.684747 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 029a23112..8be847ad7 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: 0.018223
- Baseline: 3.524503
+ Numpy running time: 0.018026
+ Baseline: 3.275190
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.297080
+ Opt1: 0.300694
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.328934
+ Opt2: 0.329160
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.114862
+ Opt3: 0.117921
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.111236
+ Opt4: 0.112021
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111643
+ Opt5: 0.111304
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.144929
+ Opt6: 0.144713
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 e3854140f..31053f36c 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
=================
-**00:35.179** total execution time for **how_to_optimize_operators** files:
+**00:34.494** total execution time for **how_to_optimize_operators** files:
-- **00:32.555**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.396**: :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``)
+- **00:31.832**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.448**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.215**: :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 7b25e3f06..c1decc360 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
=================
-**05:02.667** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:27.183**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.913**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.029**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.815**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.462**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.266**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**04:58.076** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:26.085**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:19.147**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.043**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:15.871**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.535**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.395**: :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 c73231e9b..d4a5b7321 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
@@ -222,97 +222,1351 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), 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" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 16), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 48), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dt [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer) + 129024)]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 9)*7)) + (floormod(blockIdx.x, 7)*7 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 32), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 32), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 96), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 96), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 96), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 160), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 160), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 160), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + floo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + (floormod(blockIdx.x, 7)*7)) + fl [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + (threadIdx.x_2 + 32))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 292), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 300), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 316), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 332), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 340), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 348), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 356), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 372), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 380), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 388), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 404), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 412), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 428), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 436), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 444), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 452), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 460), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 484), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 492), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 500), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 508), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 516), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 524), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 548), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 556), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 564), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 572), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -365,7 +1619,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.413 ms
+ Execution time of this operator: 0.257 ms
@@ -409,37 +1663,37 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ 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=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_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_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
- conv2d_nchw_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=3)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+ conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
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=16)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
- compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+ compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -458,14 +1712,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -483,82 +1737,1197 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[768];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer) + 129024)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= ((((((int)threadIdx.x) + 5) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 5) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= ((((((int)threadIdx.x) + 15) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 15) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) + 15) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] [...]
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((1 <= ((((((int)threadIdx.x) + 25) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 25) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] [...]
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : [...]
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2400) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2976) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3552) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
@@ -617,7 +2986,7 @@ 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 27.183 seconds)
+ **Total running time of the script:** ( 2 minutes 26.085 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 62a7671a1..86a3eeabe 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
@@ -614,7 +614,7 @@ 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)
- 9.9670 9.9606 10.0306 9.9100 0.0494
+ 9.5660 9.5569 9.5919 9.5492 0.0186
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 8cf8aa4f4..23d2b03d7 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
@@ -633,7 +633,7 @@ 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)
- 755.3439 753.5566 759.6341 752.8411 3.0476
+ 752.9251 750.6992 759.9661 748.1100 5.0897
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.913 seconds)
+ **Total running time of the script:** ( 1 minutes 19.147 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 ebb9d48c4..1c25f9c1f 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
@@ -362,28 +362,76 @@ 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], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
+ {
+ compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
for (i.inner: int32, 0, 4) {
- 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*64) + (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)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*64) + (i.inner*16))
+ let cse_var_18: int32 = (cse_var_19 + 10)
+ let cse_var_17: int32 = (cse_var_19 + 11)
+ let cse_var_16: int32 = (cse_var_19 + 12)
+ let cse_var_15: int32 = (cse_var_19 + 13)
+ let cse_var_14: int32 = (cse_var_19 + 14)
+ let cse_var_13: int32 = (cse_var_19 + 15)
+ let cse_var_12: int32 = (cse_var_19 + 2)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 4)
+ let cse_var_9: int32 = (cse_var_19 + 5)
+ let cse_var_8: int32 = (cse_var_19 + 6)
+ let cse_var_7: int32 = (cse_var_19 + 7)
+ let cse_var_6: int32 = (cse_var_19 + 8)
+ let cse_var_5: int32 = (cse_var_19 + 9)
+ let cse_var_4: int32 = (cse_var_19 + 1)
+ let cse_var_3: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.outer.inner*1024)) + (i.inner*256))
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_22, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -437,7 +485,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.474 ms
+ Execution time of this operator: 1.828 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 9565b9f52..2a7f1ddb1 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
=================
-**00:44.195** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.482** total execution time for **how_to_tune_with_autotvm** files:
-- **00:43.373**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.217**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.205**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.200**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.622**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.223**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.217**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.211**: :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_arm.py` (``tune_relay_arm.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 dcaee000d..7d82d63a6 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: 102.59/102.59 result: MeasureResult(costs=(0.0022566282291666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5949983596801758, timestamp=1650690027.666691) [('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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.50/42.50 result: MeasureResult(costs=(0.005446518210526316,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5788905620574951, timestamp=1650788920.652944) [('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: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.50 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: 0x00007f48339cefa2
+ 12: 0x00007fdcf9cebfa2
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: 142.38/142.38 result: MeasureResult(costs=(0.0016259662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.420372486114502, timestamp=1650690054.0953064) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+ No: 20 GFLOPS: 144.45/144.45 result: MeasureResult(costs=(0.00160269044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4209423065185547, timestamp=1650788946.9838886) [('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: 0.001982
+ Time cost of this operator: 0.002066
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 34f54accf..fcf91032c 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
@@ -292,10 +292,10 @@ 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 312.8 98.738 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.97 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.292 (1, 1, 10, 10, 3) 1 1
- Total_time - 316.798 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.6 98.768 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.945 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.913 0.287 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.513 - - - -
@@ -357,10 +357,10 @@ 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 81.0 96.817 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.728 2.065 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 1.118 (1, 1, 10, 10, 3) 1 1
- Total_time - 83.663 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.8 96.81 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 2.097 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.924 1.093 (1, 1, 10, 10, 3) 1 1
+ Total_time - 84.496 - - - -
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 c12a6f7e5..720613a48 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
=================
-**00:44.000** total execution time for **how_to_work_with_microtvm** files:
+**00:43.859** total execution time for **how_to_work_with_microtvm** files:
-- **00:39.918**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.494**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.191**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.190**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:39.815**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.447**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.203**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
+- **00:00.201**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.192**: :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 ebc8fb17d..d16d93185 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
=================
-**00:09.154** total execution time for **how_to_work_with_relay** files:
+**00:08.880** total execution time for **how_to_work_with_relay** files:
-- **00:07.437**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.503**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.214**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:06.841**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.817**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.222**: :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 ad328af6b..9d5352847 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
=================
-**00:05.549** total execution time for **how_to_work_with_schedules** files:
+**00:05.541** total execution time for **how_to_work_with_schedules** files:
-- **00:02.037**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.145**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.713**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.690**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.298**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.227**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.224**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.217**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.058**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.087**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.721**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.703**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.296**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.241**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.224**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.211**: :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 3411e7fa0..67825af7b 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/tmp6yusbrem/input0.cc'\nsource_filename = \"/tmp/tmp6yusbrem/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/tmpqk99po7x/input0.cc'\nsource_filename = \"/tmp/tmpqk99po7x/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 44e73c730..8798608b3 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
=================
-**00:20.754** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.263** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.557**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:20.066**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
- **00:00.197**: :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 1e324867f..4503dadb2 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ 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 20.94s!
+ resnet18_v1 inference graph built in 21.15s!
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 132beddbf..01d72ed32 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:439: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 14.56s!
+ yolov3-tiny inference graph built in 14.73s!
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 529dd8262..7cfeea508 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
=================
-**01:27.989** total execution time for **topic_vta_tutorials_frontend** files:
+**01:27.967** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.818**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.170**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.716**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.251**: :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 b0fbf5c43..2b63b8d62 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
=================
-**00:03.767** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.509** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.229**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.538**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.975**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.533**: :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 815b9cd7a..565a22aee 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
=================
-**00:00.976** total execution time for **topic_vta_tutorials** files:
+**00:00.974** total execution time for **topic_vta_tutorials** files:
-- **00:00.499**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.477**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.489**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.486**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 6c79e7090..fcf67a559 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
-
+ *E
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.729 ms
+ Execution time of this operator: 93.853 ms
@@ -417,7 +417,7 @@ operations.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 3.810 seconds)
+ **Total running time of the script:** ( 1 minutes 13.354 seconds)
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 202fbd570..079b1b2cf 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -268,7 +268,7 @@ standard deviation.
.. code-block:: none
- {'mean': 492.6316053099993, 'median': 492.4662148999971, 'std': 0.45000288160307683}
+ {'mean': 492.4382142399998, 'median': 492.1501486500006, 'std': 0.944031885621179}
@@ -482,32 +482,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 17.15/ 23.91 GFLOPS | Progress: (4/10) | 4.81 s
[Task 1/25] Current/Best: 5.81/ 23.91 GFLOPS | Progress: (8/10) | 8.61 s
[Task 1/25] Current/Best: 16.74/ 23.91 GFLOPS | Progress: (10/10) | 9.73 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 17.55/ 17.55 GFLOPS | Progress: (4/10) | 2.70 s
[Task 2/25] Current/Best: 14.91/ 20.17 GFLOPS | Progress: (8/10) | 3.87 s
[Task 2/25] Current/Best: 20.68/ 20.68 GFLOPS | Progress: (10/10) | 4.35 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 17.86/ 18.99 GFLOPS | Progress: (4/10) | 2.68 s
[Task 3/25] Current/Best: 7.63/ 22.54 GFLOPS | Progress: (8/10) | 4.62 s
[Task 3/25] Current/Best: 14.78/ 22.54 GFLOPS | Progress: (10/10) | 5.56 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 11.82/ 14.62 GFLOPS | Progress: (4/10) | 5.69 s
[Task 4/25] Current/Best: 13.01/ 14.71 GFLOPS | Progress: (8/10) | 7.52 s
[Task 4/25] Current/Best: 14.33/ 16.94 GFLOPS | Progress: (10/10) | 8.30 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 11.36/ 16.91 GFLOPS | Progress: (4/10) | 2.63 s
[Task 5/25] Current/Best: 5.16/ 19.29 GFLOPS | Progress: (8/10) | 4.47 s
[Task 5/25] Current/Best: 9.76/ 19.29 GFLOPS | Progress: (10/10) | 5.14 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 16.33/ 16.33 GFLOPS | Progress: (4/10) | 3.11 s
[Task 6/25] Current/Best: 10.78/ 16.33 GFLOPS | Progress: (8/10) | 6.33 s
[Task 6/25] Current/Best: 13.49/ 18.21 GFLOPS | Progress: (10/10) | 7.05 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 10.59/ 21.24 GFLOPS | Progress: (4/10) | 2.67 s
[Task 7/25] Current/Best: 6.48/ 21.24 GFLOPS | Progress: (8/10) | 4.80 s
[Task 7/25] Current/Best: 6.72/ 21.24 GFLOPS | Progress: (10/10) | 5.96 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 12.71/ 22.83 GFLOPS | Progress: (4/10) | 2.95 s
[Task 8/25] Current/Best: 8.97/ 22.83 GFLOPS | Progress: (8/10) | 5.86 s
[Task 8/25] Current/Best: 5.73/ 22.83 GFLOPS | Progress: (10/10) | 6.93 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 9.99/ 20.35 GFLOPS | Progress: (4/10) | 4.60 s
[Task 9/25] Current/Best: 11.69/ 20.35 GFLOPS | Progress: (8/10) | 6.14 s
[Task 9/25] Current/Best: 12.63/ 20.35 GFLOPS | Progress: (10/10) | 15.62 s Done.
-
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 14.13/ 20.33 GFLOPS | Progress: (4/10) | 2.35 s
[Task 10/25] Current/Best: 19.04/ 20.33 GFLOPS | Progress: (8/10) | 4.01 s
[Task 10/25] Current/Best: 19.21/ 20.33 GFLOPS | Progress: (10/10) | 5.13 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 18.01/ 18.01 GFLOPS | Progress: (4/10) | 3.35 s
[Task 11/25] Current/Best: 12.37/ 20.88 GFLOPS | Progress: (8/10) | 5.39 s
[Task 11/25] Current/Best: 1.59/ 20.88 GFLOPS | Progress: (10/10) | 7.66 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 10.73/ 20.18 GFLOPS | Progress: (4/10) | 2.98 s
[Task 12/25] Current/Best: 13.21/ 20.18 GFLOPS | Progress: (8/10) | 6.33 s
[Task 12/25] Current/Best: 16.36/ 20.18 GFLOPS | Progress: (10/10) | 7.35 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 11.47/ 11.47 GFLOPS | Progress: (4/10) | 5.08 s
[Task 13/25] Current/Best: 4.74/ 15.17 GFLOPS | Progress: (8/10) | 8.45 s
[Task 13/25] Current/Best: 18.73/ 18.73 GFLOPS | Progress: (10/10) | 10.62 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 14.51/ 16.34 GFLOPS | Progress: (4/10) | 3.94 s
[Task 14/25] Current/Best: 7.15/ 16.34 GFLOPS | Progress: (8/10) | 7.10 s
[Task 14/25] Current/Best: 13.16/ 19.19 GFLOPS | Progress: (10/10) | 7.86 s Done.
-
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 10.18/ 23.21 GFLOPS | Progress: (4/10) | 2.91 s
[Task 15/25] Current/Best: 17.88/ 23.21 GFLOPS | Progress: (8/10) | 4.53 s
[Task 15/25] Current/Best: 18.97/ 23.21 GFLOPS | Progress: (10/10) | 5.31 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 15.88/ 15.88 GFLOPS | Progress: (4/10) | 2.91 s
[Task 16/25] Current/Best: 6.17/ 15.88 GFLOPS | Progress: (8/10) | 4.91 s
[Task 16/25] Current/Best: 10.18/ 15.88 GFLOPS | Progress: (10/10) | 7.78 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 20.55/ 20.55 GFLOPS | Progress: (4/10) | 3.11 s
[Task 17/25] Current/Best: 10.25/ 20.55 GFLOPS | Progress: (8/10) | 6.04 s
[Task 17/25] Current/Best: 7.50/ 20.55 GFLOPS | Progress: (10/10) | 8.26 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 9.55/ 19.41 GFLOPS | Progress: (4/10) | 3.16 s
[Task 18/25] Current/Best: 17.21/ 22.12 GFLOPS | Progress: (8/10) | 4.74 s
[Task 18/25] Current/Best: 16.47/ 22.12 GFLOPS | Progress: (10/10) | 5.95 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 10.75/ 21.84 GFLOPS | Progress: (4/10) | 3.63 s
[Task 19/25] Current/Best: 5.30/ 21.84 GFLOPS | Progress: (8/10) | 7.32 s
[Task 19/25] Current/Best: 22.77/ 22.77 GFLOPS | Progress: (10/10) | 8.56 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 5.34/ 16.10 GFLOPS | Progress: (4/10) | 3.22 s
[Task 20/25] Current/Best: 8.96/ 16.10 GFLOPS | Progress: (8/10) | 4.64 s
[Task 20/25] Current/Best: 5.19/ 16.10 GFLOPS | Progress: (10/10) | 9.68 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 1/25] Current/Best: 19.18/ 19.18 GFLOPS | Progress: (4/10) | 4.99 s
[Task 1/25] Current/Best: 10.57/ 19.18 GFLOPS | Progress: (8/10) | 7.28 s
[Task 1/25] Current/Best: 17.23/ 19.18 GFLOPS | Progress: (10/10) | 8.47 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 2/25] Current/Best: 22.61/ 22.61 GFLOPS | Progress: (4/10) | 1.94 s
[Task 2/25] Current/Best: 13.54/ 22.61 GFLOPS | Progress: (8/10) | 3.10 s
[Task 2/25] Current/Best: 15.02/ 22.61 GFLOPS | Progress: (10/10) | 3.61 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 3/25] Current/Best: 11.16/ 24.05 GFLOPS | Progress: (4/10) | 2.94 s
[Task 3/25] Current/Best: 16.66/ 24.05 GFLOPS | Progress: (8/10) | 4.74 s
[Task 3/25] Current/Best: 6.28/ 24.05 GFLOPS | Progress: (10/10) | 5.72 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 4/25] Current/Best: 16.57/ 17.51 GFLOPS | Progress: (4/10) | 8.73 s
[Task 4/25] Current/Best: 10.52/ 17.51 GFLOPS | Progress: (8/10) | 10.37 s
[Task 4/25] Current/Best: 22.17/ 22.17 GFLOPS | Progress: (10/10) | 11.00 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 5/25] Current/Best: 12.31/ 14.56 GFLOPS | Progress: (4/10) | 2.78 s
[Task 5/25] Current/Best: 13.56/ 14.56 GFLOPS | Progress: (8/10) | 4.57 s
[Task 5/25] Current/Best: 4.00/ 15.28 GFLOPS | Progress: (10/10) | 5.46 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 6/25] Current/Best: 3.89/ 12.98 GFLOPS | Progress: (4/10) | 3.91 s
[Task 6/25] Current/Best: 12.58/ 19.20 GFLOPS | Progress: (8/10) | 7.23 s
[Task 6/25] Current/Best: 4.62/ 19.20 GFLOPS | Progress: (10/10) | 8.58 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 7/25] Current/Best: 14.32/ 17.07 GFLOPS | Progress: (4/10) | 3.16 s
[Task 7/25] Current/Best: 18.81/ 23.40 GFLOPS | Progress: (8/10) | 5.08 s
[Task 7/25] Current/Best: 6.30/ 23.40 GFLOPS | Progress: (10/10) | 6.24 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 8/25] Current/Best: 8.42/ 12.23 GFLOPS | Progress: (4/10) | 3.36 s
[Task 8/25] Current/Best: 3.17/ 20.31 GFLOPS | Progress: (8/10) | 5.72 s
[Task 8/25] Current/Best: 11.47/ 20.31 GFLOPS | Progress: (10/10) | 7.51 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 9/25] Current/Best: 6.10/ 16.85 GFLOPS | Progress: (4/10) | 8.08 s
[Task 9/25] Current/Best: 11.79/ 23.29 GFLOPS | Progress: (8/10) | 9.56 s
[Task 9/25] Current/Best: 17.77/ 23.29 GFLOPS | Progress: (10/10) | 10.44 s Done.
+
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 10/25] Current/Best: 13.58/ 13.58 GFLOPS | Progress: (4/10) | 3.51 s
[Task 10/25] Current/Best: 5.63/ 18.31 GFLOPS | Progress: (8/10) | 5.78 s
[Task 10/25] Current/Best: 11.97/ 18.31 GFLOPS | Progress: (10/10) | 6.75 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 11/25] Current/Best: 10.46/ 14.81 GFLOPS | Progress: (4/10) | 3.24 s
[Task 11/25] Current/Best: 18.76/ 18.76 GFLOPS | Progress: (8/10) | 5.63 s
[Task 11/25] Current/Best: 17.26/ 18.76 GFLOPS | Progress: (10/10) | 6.80 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 12/25] Current/Best: 4.80/ 11.01 GFLOPS | Progress: (4/10) | 4.37 s
[Task 12/25] Current/Best: 15.01/ 15.01 GFLOPS | Progress: (8/10) | 7.55 s
[Task 12/25] Current/Best: 4.85/ 15.01 GFLOPS | Progress: (10/10) | 8.81 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 13/25] Current/Best: 13.28/ 15.81 GFLOPS | Progress: (4/10) | 3.18 s
[Task 13/25] Current/Best: 19.18/ 20.54 GFLOPS | Progress: (8/10) | 5.00 s
[Task 13/25] Current/Best: 8.67/ 20.54 GFLOPS | Progress: (10/10) | 6.11 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 14/25] Current/Best: 14.15/ 16.04 GFLOPS | Progress: (4/10) | 2.97 s
[Task 14/25] Current/Best: 13.52/ 16.78 GFLOPS | Progress: (8/10) | 4.93 s
[Task 14/25] Current/Best: 18.85/ 18.85 GFLOPS | Progress: (10/10) | 5.86 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 15/25] Current/Best: 18.57/ 20.64 GFLOPS | Progress: (4/10) | 2.76 s
[Task 15/25] Current/Best: 3.19/ 20.64 GFLOPS | Progress: (8/10) | 4.71 s
[Task 15/25] Current/Best: 14.97/ 20.64 GFLOPS | Progress: (10/10) | 5.29 s Done.
+
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 16/25] Current/Best: 16.87/ 21.81 GFLOPS | Progress: (4/10) | 2.13 s
[Task 16/25] Current/Best: 23.10/ 23.10 GFLOPS | Progress: (8/10) | 4.60 s
[Task 16/25] Current/Best: 13.47/ 23.10 GFLOPS | Progress: (10/10) | 6.41 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 17/25] Current/Best: 15.20/ 15.20 GFLOPS | Progress: (4/10) | 3.12 s
[Task 17/25] Current/Best: 14.36/ 15.20 GFLOPS | Progress: (8/10) | 6.35 s
[Task 17/25] Current/Best: 17.86/ 17.86 GFLOPS | Progress: (10/10) | 7.26 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 18/25] Current/Best: 22.36/ 22.36 GFLOPS | Progress: (4/10) | 4.98 s Done.
+
[Task 18/25] Current/Best: 10.71/ 23.73 GFLOPS | Progress: (8/10) | 7.73 s
[Task 18/25] Current/Best: 6.90/ 23.73 GFLOPS | Progress: (10/10) | 8.62 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 19/25] Current/Best: 7.17/ 19.51 GFLOPS | Progress: (4/10) | 5.58 s
[Task 19/25] Current/Best: 10.93/ 19.51 GFLOPS | Progress: (8/10) | 12.33 s
[Task 19/25] Current/Best: 6.86/ 19.51 GFLOPS | Progress: (10/10) | 13.67 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 20/25] Current/Best: 4.27/ 15.01 GFLOPS | Progress: (4/10) | 3.53 s
[Task 20/25] Current/Best: 6.28/ 15.79 GFLOPS | Progress: (8/10) | 5.11 s
[Task 20/25] Current/Best: 9.16/ 15.79 GFLOPS | Progress: (10/10) | 7.33 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 21/25] Current/Best: 5.95/ 23.19 GFLOPS | Progress: (4/10) | 2.96 s
[Task 21/25] Current/Best: 19.90/ 23.19 GFLOPS | Progress: (8/10) | 4.82 s
[Task 21/25] Current/Best: 10.26/ 23.19 GFLOPS | Progress: (10/10) | 5.37 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 6.76/ 21.51 GFLOPS | Progress: (4/10) | 3.33 s
[Task 22/25] Current/Best: 5.32/ 21.51 GFLOPS | Progress: (8/10) | 5.04 s
[Task 22/25] Current/Best: 4.85/ 21.51 GFLOPS | Progress: (10/10) | 5.80
s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 24.02/ 24.02 GFLOPS | Progress: (4/10) | 2.57 s
[Task 23/25] Current/Best: 9.14/ 24.02 GFLOPS | Progress: (8/10) | 8.07 s
[Task 23/25] Current/Best: 11.09/ 24.02 GFLOPS | Progress: (10/10) | 9.46 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 5.56/ 9.25 GFLOPS | Progress: (4/10) | 2.74 s
[Task 24/25] Current/Best: 0.94/ 9.25 GFLOPS | Progress: (8/10) | 15.78 s
[Task 24/25] Current/Best: 5.70/ 9.25 GFLOPS | Progress: (10/10) | 16.31 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 21/25] Current/Best: 7.00/ 17.83 GFLOPS | Progress: (4/10) | 3.10 s
[Task 21/25] Current/Best: 8.89/ 23.44 GFLOPS | Progress: (8/10) | 4.91 s
[Task 21/25] Current/Best: 0.00/ 23.44 GFLOPS | Progress: (10/10) | 5.53 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 22/25] Current/Best: 18.58/ 21.71 GFLOPS | Progress: (4/10) | 2.65 s
[Task 22/25] Current/Best: 14.79/ 21.71 GFLOPS | Progress: (8/10) | 4.44 s
[Task 22/25] Current/Best: 5.94/ 21.71 GFLOPS | Progress: (10/10) | 6.47 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 23/25] Current/Best: 22.80/ 22.80 GFLOPS | Progress: (4/10) | 5.67 s
[Task 23/25] Current/Best: 20.16/ 22.80 GFLOPS | Progress: (8/10) | 8.49 s
[Task 23/25] Current/Best: 7.01/ 22.80 GFLOPS | Progress: (10/10) | 10.75 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s
[Task 24/25] Current/Best: 1.97/ 4.99 GFLOPS | Progress: (4/10) | 12.00 s
[Task 24/25] Current/Best: 8.84/ 10.59 GFLOPS | Progress: (8/10) | 24.16 s
[Task 24/25] Current/Best: 1.15/ 10.59 GFLOPS | Progress: (10/10) | 26.93 s
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/10) | 0.00 s Done.
Done.
-
[Task 25/25] Current/Best: 5.10/ 8.37 GFLOPS | Progress: (4/10) | 3.96 s
[Task 25/25] Current/Best: 3.50/ 8.37 GFLOPS | Progress: (8/10) | 12.39 s
[Task 25/25] Current/Best: 1.48/ 9.49 GFLOPS | Progress: (10/10) | 17.37 s Done.
-
+
[Task 25/25] Current/Best: 5.53/ 5.53 GFLOPS | Progress: (4/10) | 2.94 s
[Task 25/25] Current/Best: 5.99/ 5.99 GFLOPS | Progress: (8/10) | 28.48 s
[Task 25/25] Current/Best: 7.85/ 7.85 GFLOPS | Progress: (10/10) | 32.78 s
The output from this tuning process will look something like this:
@@ -649,8 +648,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 433.3818005000001, 'median': 433.01172650000126, 'std': 1.2187799667414965}
- unoptimized: {'mean': 492.6316053099993, 'median': 492.4662148999971, 'std': 0.45000288160307683}
+ optimized: {'mean': 492.56040461999874, 'median': 492.6452632500059, 'std': 0.6243796737694035}
+ unoptimized: {'mean': 492.4382142399998, 'median': 492.1501486500006, 'std': 0.944031885621179}
@@ -670,7 +669,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 6 minutes 51.260 seconds)
+ **Total running time of the script:** ( 6 minutes 56.969 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 135fdb4a6..54fafb972 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
- 1.239e-07 secs/op
+ 1.191e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 45b1b07d8..155b232d9 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, 0x207ddba0)), stage(b, placeholder(b, 0x1a5492f0)), 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, 0x8056d20)), stage(b, placeholder(b, 0xc7f4490)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min= [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 3d3ea21bb..24d76dfad 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
=================
-**09:45.828** total execution time for **tutorial** files:
+**09:55.226** total execution time for **tutorial** files:
-- **06:51.260**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:03.810**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **01:00.772**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:25.543**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:22.333**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.089**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.718**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.176**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.034**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.032**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **06:56.969**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:13.354**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:59.137**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:25.667**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:17.933**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:01.155**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.698**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.188**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.037**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
- **00:00.031**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.030**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
- **00:00.029**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index 49dcfa436..4fb5db2b1 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -335,7 +335,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000006
@@ -388,7 +388,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000026
+ 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"),
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.116219999010354e-06 1.0
- naive 5.8296e-06 0.7182653994976514
- parallel 7.0317e-06 0.866376219577267
- vector 2.5753399999999996e-05 3.173078108176001
+ numpy 8.04313000116963e-06 1.0
+ naive 5.8392e-06 0.7259860277219023
+ parallel 6.0565e-06 0.753002873150038
+ vector 2.44941e-05 3.0453442871665724
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.017579
+ Numpy running time: 0.018094
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.421662
+ none: 3.286055
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.299119
+ blocking: 0.301606
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.335124
+ vectorization: 0.337414
@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], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.112224
+ loop permutation: 0.114399
@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], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.107586
+ array packing: 0.108287
@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], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.110072
+ block caching: 0.109145
@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], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.143778
+ parallelization: 0.143666
@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], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4216618965000003 1.0
- blocking 0.2991194263 0.08741934046901818
- vectorization 0.3351239071 0.09794185318040817
- loop permutation 0.1122239282 0.0327980763718336
- array packing 0.1075860693 0.03144263593374004
- block caching 0.11007208180000001 0.03216918711711177
- parallelization 0.143777803 0.04201987436194954
+ none 3.2860548506000002 1.0
+ blocking 0.30160568870000004 0.09178352231245619
+ vectorization 0.33741425880000003 0.10268065328805806
+ loop permutation 0.1143989916 0.03481347597685775
+ array packing 0.10828706259999998 0.03295351645765373
+ block caching 0.1091447533 0.03321452570399769
+ parallelization 0.14366594159999999 0.04371988543458672
@@ -1541,11 +1541,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 0.772 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 6efa18321..dedbd2c0b 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-bce57586bd3e41ea3c38a157c126f1fea40a8313
+822d863770f17d0aa2e37fb128438eb4b483d1f1
diff --git a/docs/how_to/compile_models/from_darknet.html b/docs/how_to/compile_models/from_darknet.html
index c1cf81d8a..8390f3b14 100644
--- a/docs/how_to/compile_models/from_darknet.html
+++ b/docs/how_to/compile_models/from_darknet.html
@@ -549,6 +549,7 @@ class:['truck 0.9266'] left:471 right:83 top:689 bottom:169
class:['bicycle 0.9984'] left:111 right:113 top:577 bottom:447
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.135 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-darknet-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7716f96385bd5abb6e822041e285be54/from_darknet.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_darknet.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 113fe41f9..150d39d7d 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.zip67880911-6b49-4538-938a-4b8f125626ab 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.zip0f941fee-8e3c-43fa-be3d-5d28049a2f8a 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 fdb24feca..f3021a291 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,101 +406,58 @@ 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<08:23, 86.3kB/s]
- 0%| | 48.0k/41.5M [00:00<05:20, 135kB/s]
- 0%| | 104k/41.5M [00:00<03:28, 208kB/s]
- 0%| | 208k/41.5M [00:00<02:07, 339kB/s]
- 1%| | 288k/41.5M [00:00<01:38, 437kB/s]
- 1%| | 416k/41.5M [00:00<01:08, 633kB/s]
- 1%|1 | 528k/41.5M [00:01<00:57, 744kB/s]
- 2%|1 | 672k/41.5M [00:01<00:46, 911kB/s]
- 2%|1 | 792k/41.5M [00:01<00:44, 957kB/s]
- 2%|2 | 936k/41.5M [00:01<00:40, 1.06MB/s]
- 2%|2 | 1.03M/41.5M [00:01<00:40, 1.06MB/s]
- 3%|2 | 1.19M/41.5M [00:01<00:35, 1.19MB/s]
- 3%|3 | 1.31M/41.5M [00:01<00:35, 1.17MB/s]
- 4%|3 | 1.48M/41.5M [00:01<00:31, 1.31MB/s]
- 4%|3 | 1.61M/41.5M [00:01<00:32, 1.28MB/s]
- 5%|4 | 1.91M/41.5M [00:02<00:30, 1.38MB/s]
- 5%|5 | 2.23M/41.5M [00:02<00:24, 1.70MB/s]
- 6%|5 | 2.41M/41.5M [00:02<00:23, 1.72MB/s]
- 6%|6 | 2.58M/41.5M [00:02<00:27, 1.47MB/s]
- 7%|6 | 2.77M/41.5M [00:02<00:25, 1.57MB/s]
- 7%|7 | 2.92M/41.5M [00:02<00:26, 1.52MB/s]
- 8%|7 | 3.12M/41.5M [00:02<00:24, 1.66MB/s]
- 8%|7 | 3.29M/41.5M [00:03<00:24, 1.64MB/s]
- 9%|8 | 3.68M/41.5M [00:03<00:21, 1.81MB/s]
- 10%|9 | 4.09M/41.5M [00:03<00:20, 1.92MB/s]
- 11%|# | 4.52M/41.5M [00:03<00:19, 2.03MB/s]
- 12%|#1 | 4.96M/41.5M [00:03<00:16, 2.35MB/s]
- 13%|#2 | 5.23M/41.5M [00:03<00:17, 2.23MB/s]
- 13%|#3 | 5.45M/41.5M [00:04<00:17, 2.12MB/s]
- 14%|#4 | 5.92M/41.5M [00:04<00:14, 2.50MB/s]
- 15%|#4 | 6.21M/41.5M [00:04<00:14, 2.60MB/s]
- 16%|#5 | 6.47M/41.5M [00:04<00:16, 2.26MB/s]
- 16%|#6 | 6.74M/41.5M [00:04<00:15, 2.39MB/s]
- 17%|#6 | 6.98M/41.5M [00:04<00:15, 2.33MB/s]
- 18%|#7 | 7.30M/41.5M [00:04<00:14, 2.54MB/s]
- 18%|#8 | 7.55M/41.5M [00:04<00:14, 2.47MB/s]
- 19%|#8 | 7.88M/41.5M [00:05<00:13, 2.70MB/s]
- 20%|#9 | 8.14M/41.5M [00:05<00:13, 2.67MB/s]
- 20%|## | 8.46M/41.5M [00:05<00:12, 2.86MB/s]
- 21%|##1 | 8.74M/41.5M [00:05<00:12, 2.79MB/s]
- 22%|##1 | 9.09M/41.5M [00:05<00:11, 2.93MB/s]
- 23%|##2 | 9.37M/41.5M [00:05<00:12, 2.80MB/s]
- 23%|##3 | 9.73M/41.5M [00:05<00:10, 3.05MB/s]
- 24%|##4 | 10.0M/41.5M [00:05<00:11, 2.96MB/s]
- 25%|##5 | 10.4M/41.5M [00:05<00:10, 3.23MB/s]
- 26%|##5 | 10.7M/41.5M [00:06<00:10, 3.17MB/s]
- 27%|##6 | 11.1M/41.5M [00:06<00:09, 3.38MB/s]
- 28%|##7 | 11.5M/41.5M [00:06<00:09, 3.32MB/s]
- 29%|##8 | 11.9M/41.5M [00:06<00:08, 3.56MB/s]
- 29%|##9 | 12.2M/41.5M [00:06<00:08, 3.55MB/s]
- 31%|### | 12.7M/41.5M [00:06<00:08, 3.72MB/s]
- 31%|###1 | 13.0M/41.5M [00:06<00:08, 3.66MB/s]
- 32%|###2 | 13.5M/41.5M [00:06<00:07, 3.85MB/s]
- 33%|###3 | 13.8M/41.5M [00:06<00:07, 3.75MB/s]
- 34%|###4 | 14.3M/41.5M [00:06<00:07, 4.00MB/s]
- 35%|###5 | 14.7M/41.5M [00:07<00:07, 3.88MB/s]
- 37%|###6 | 15.2M/41.5M [00:07<00:06, 4.22MB/s]
- 38%|###7 | 15.6M/41.5M [00:07<00:06, 4.14MB/s]
- 39%|###8 | 16.1M/41.5M [00:07<00:05, 4.51MB/s]
- 40%|###9 | 16.6M/41.5M [00:07<00:05, 4.38MB/s]
- 41%|####1 | 17.1M/41.5M [00:07<00:05, 4.69MB/s]
- 42%|####2 | 17.6M/41.5M [00:07<00:05, 4.58MB/s]
- 44%|####3 | 18.1M/41.5M [00:07<00:05, 4.80MB/s]
- 45%|####4 | 18.6M/41.5M [00:07<00:05, 4.58MB/s]
- 46%|####6 | 19.2M/41.5M [00:08<00:04, 4.97MB/s]
- 47%|####7 | 19.7M/41.5M [00:08<00:04, 4.96MB/s]
- 49%|####8 | 20.3M/41.5M [00:08<00:04, 5.38MB/s]
- 50%|##### | 20.8M/41.5M [00:08<00:04, 5.38MB/s]
- 52%|#####1 | 21.5M/41.5M [00:08<00:03, 5.81MB/s]
- 53%|#####3 | 22.1M/41.5M [00:08<00:03, 5.79MB/s]
- 55%|#####4 | 22.7M/41.5M [00:08<00:03, 6.08MB/s]
- 56%|#####6 | 23.3M/41.5M [00:08<00:03, 6.05MB/s]
- 58%|#####7 | 24.0M/41.5M [00:08<00:02, 6.29MB/s]
- 59%|#####9 | 24.6M/41.5M [00:09<00:02, 6.26MB/s]
- 61%|######1 | 25.3M/41.5M [00:09<00:02, 6.55MB/s]
- 63%|######2 | 26.0M/41.5M [00:09<00:02, 6.51MB/s]
- 64%|######4 | 26.8M/41.5M [00:09<00:02, 6.90MB/s]
- 66%|######6 | 27.4M/41.5M [00:09<00:02, 6.79MB/s]
- 68%|######8 | 28.2M/41.5M [00:09<00:01, 7.25MB/s]
- 70%|######9 | 28.9M/41.5M [00:09<00:01, 7.14MB/s]
- 72%|#######2 | 29.9M/41.5M [00:09<00:01, 8.09MB/s]
- 74%|#######3 | 30.7M/41.5M [00:09<00:01, 8.05MB/s]
- 76%|#######5 | 31.5M/41.5M [00:09<00:01, 8.18MB/s]
- 78%|#######7 | 32.3M/41.5M [00:10<00:01, 7.88MB/s]
- 80%|#######9 | 33.1M/41.5M [00:10<00:01, 7.88MB/s]
- 81%|########1 | 33.8M/41.5M [00:10<00:01, 7.53MB/s]
- 84%|########3 | 34.7M/41.5M [00:10<00:00, 7.60MB/s]
- 86%|########5 | 35.5M/41.5M [00:10<00:00, 7.87MB/s]
- 87%|########7 | 36.3M/41.5M [00:10<00:00, 6.91MB/s]
- 91%|######### | 37.6M/41.5M [00:10<00:00, 8.30MB/s]
- 93%|#########2| 38.4M/41.5M [00:10<00:00, 8.34MB/s]
- 95%|#########4| 39.2M/41.5M [00:11<00:00, 6.81MB/s]
- 97%|#########7| 40.4M/41.5M [00:11<00:00, 8.06MB/s]
- 99%|#########9| 41.2M/41.5M [00:11<00:00, 8.05MB/s]
-100%|##########| 41.5M/41.5M [00:11<00:00, 3.84MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:04, 89.8kB/s]
+ 0%| | 48.0k/41.5M [00:00<05:05, 142kB/s]
+ 0%| | 80.0k/41.5M [00:00<04:33, 159kB/s]
+ 0%| | 152k/41.5M [00:00<02:50, 255kB/s]
+ 1%| | 312k/41.5M [00:00<01:29, 485kB/s]
+ 1%|1 | 632k/41.5M [00:01<00:46, 928kB/s]
+ 2%|2 | 976k/41.5M [00:01<00:33, 1.25MB/s]
+ 3%|3 | 1.30M/41.5M [00:01<00:28, 1.48MB/s]
+ 4%|4 | 1.66M/41.5M [00:01<00:24, 1.67MB/s]
+ 5%|4 | 2.05M/41.5M [00:01<00:22, 1.83MB/s]
+ 6%|5 | 2.45M/41.5M [00:02<00:20, 1.97MB/s]
+ 7%|6 | 2.87M/41.5M [00:02<00:19, 2.10MB/s]
+ 8%|7 | 3.30M/41.5M [00:02<00:18, 2.22MB/s]
+ 9%|9 | 3.77M/41.5M [00:02<00:16, 2.35MB/s]
+ 10%|# | 4.26M/41.5M [00:02<00:15, 2.49MB/s]
+ 11%|#1 | 4.77M/41.5M [00:02<00:14, 2.61MB/s]
+ 13%|#2 | 5.29M/41.5M [00:03<00:13, 2.73MB/s]
+ 14%|#4 | 5.82M/41.5M [00:03<00:13, 2.82MB/s]
+ 15%|#5 | 6.38M/41.5M [00:03<00:12, 2.94MB/s]
+ 17%|#6 | 6.98M/41.5M [00:03<00:11, 3.08MB/s]
+ 18%|#8 | 7.58M/41.5M [00:03<00:11, 3.18MB/s]
+ 20%|#9 | 8.20M/41.5M [00:04<00:10, 3.29MB/s]
+ 21%|##1 | 8.84M/41.5M [00:04<00:10, 3.41MB/s]
+ 23%|##2 | 9.53M/41.5M [00:04<00:09, 3.57MB/s]
+ 25%|##4 | 10.2M/41.5M [00:04<00:08, 3.97MB/s]
+ 26%|##6 | 11.0M/41.5M [00:04<00:07, 4.04MB/s]
+ 28%|##8 | 11.7M/41.5M [00:04<00:07, 4.16MB/s]
+ 30%|### | 12.6M/41.5M [00:05<00:07, 4.31MB/s]
+ 32%|###2 | 13.4M/41.5M [00:05<00:06, 4.48MB/s]
+ 34%|###4 | 14.3M/41.5M [00:05<00:06, 4.68MB/s]
+ 37%|###6 | 15.2M/41.5M [00:05<00:05, 5.38MB/s]
+ 38%|###8 | 15.8M/41.5M [00:05<00:04, 5.40MB/s]
+ 39%|###9 | 16.3M/41.5M [00:05<00:05, 4.62MB/s]
+ 42%|####1 | 17.3M/41.5M [00:06<00:05, 4.92MB/s]
+ 44%|####4 | 18.4M/41.5M [00:06<00:04, 5.34MB/s]
+ 47%|####6 | 19.5M/41.5M [00:06<00:04, 5.70MB/s]
+ 50%|####9 | 20.7M/41.5M [00:06<00:03, 6.00MB/s]
+ 53%|#####2 | 21.8M/41.5M [00:06<00:03, 6.23MB/s]
+ 56%|#####5 | 23.1M/41.5M [00:06<00:02, 6.47MB/s]
+ 59%|#####8 | 24.4M/41.5M [00:07<00:02, 6.77MB/s]
+ 62%|######2 | 25.7M/41.5M [00:07<00:02, 7.09MB/s]
+ 65%|######5 | 27.2M/41.5M [00:07<00:01, 8.10MB/s]
+ 69%|######9 | 28.7M/41.5M [00:07<00:01, 7.58MB/s]
+ 73%|#######2 | 30.2M/41.5M [00:07<00:01, 7.98MB/s]
+ 77%|#######6 | 31.8M/41.5M [00:08<00:01, 8.25MB/s]
+ 80%|######## | 33.3M/41.5M [00:08<00:01, 8.44MB/s]
+ 84%|########4 | 34.9M/41.5M [00:08<00:00, 8.56MB/s]
+ 88%|########7 | 36.4M/41.5M [00:08<00:00, 8.66MB/s]
+ 92%|#########1| 38.0M/41.5M [00:08<00:00, 8.73MB/s]
+ 95%|#########5| 39.6M/41.5M [00:08<00:00, 8.77MB/s]
+ 99%|#########9| 41.1M/41.5M [00:09<00:00, 8.79MB/s]
+100%|##########| 41.5M/41.5M [00:09<00:00, 4.74MB/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 3a9c4c30f..4862f2964 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ 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 11.807 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 10.337 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 89266b8e2..4d8122e6e 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,41 +387,27 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 1%|1 | 512k/44.7M [00:00<00:09, 4.97MB/s]
- 5%|4 | 2.04M/44.7M [00:00<00:03, 11.4MB/s]
- 9%|8 | 3.82M/44.7M [00:00<00:02, 14.7MB/s]
- 13%|#2 | 5.67M/44.7M [00:00<00:02, 16.5MB/s]
- 16%|#6 | 7.26M/44.7M [00:00<00:02, 14.0MB/s]
- 19%|#9 | 8.65M/44.7M [00:00<00:03, 11.9MB/s]
- 22%|##2 | 9.86M/44.7M [00:00<00:03, 10.7MB/s]
- 24%|##4 | 10.9M/44.7M [00:01<00:03, 10.1MB/s]
- 27%|##6 | 11.9M/44.7M [00:01<00:03, 10.0MB/s]
- 29%|##8 | 12.9M/44.7M [00:01<00:03, 9.61MB/s]
- 32%|###1 | 14.2M/44.7M [00:01<00:02, 10.7MB/s]
- 36%|###6 | 16.1M/44.7M [00:01<00:02, 13.1MB/s]
- 40%|#### | 17.9M/44.7M [00:01<00:02, 13.8MB/s]
- 43%|####3 | 19.2M/44.7M [00:01<00:02, 12.8MB/s]
- 46%|####6 | 20.7M/44.7M [00:01<00:01, 13.4MB/s]
- 49%|####9 | 22.0M/44.7M [00:01<00:01, 13.4MB/s]
- 52%|#####2 | 23.3M/44.7M [00:01<00:01, 13.3MB/s]
- 55%|#####5 | 24.6M/44.7M [00:02<00:01, 12.1MB/s]
- 58%|#####7 | 25.8M/44.7M [00:02<00:01, 10.6MB/s]
- 60%|###### | 26.9M/44.7M [00:02<00:01, 11.0MB/s]
- 63%|######3 | 28.3M/44.7M [00:02<00:01, 11.8MB/s]
- 66%|######6 | 29.5M/44.7M [00:02<00:01, 10.8MB/s]
- 68%|######8 | 30.5M/44.7M [00:02<00:01, 8.73MB/s]
- 71%|####### | 31.6M/44.7M [00:02<00:01, 9.15MB/s]
- 73%|#######2 | 32.5M/44.7M [00:03<00:01, 9.05MB/s]
- 76%|#######5 | 33.8M/44.7M [00:03<00:01, 9.97MB/s]
- 78%|#######8 | 35.0M/44.7M [00:03<00:00, 10.4MB/s]
- 81%|######## | 36.0M/44.7M [00:03<00:00, 10.1MB/s]
- 84%|########3 | 37.5M/44.7M [00:03<00:00, 11.3MB/s]
- 88%|########8 | 39.3M/44.7M [00:03<00:00, 12.1MB/s]
- 91%|######### | 40.5M/44.7M [00:03<00:00, 10.3MB/s]
- 93%|#########3| 41.6M/44.7M [00:03<00:00, 10.5MB/s]
- 96%|#########5| 42.7M/44.7M [00:04<00:00, 9.42MB/s]
- 99%|#########8| 44.1M/44.7M [00:04<00:00, 9.00MB/s]
-100%|##########| 44.7M/44.7M [00:04<00:00, 11.0MB/s]
+ 6%|6 | 2.69M/44.7M [00:00<00:01, 27.6MB/s]
+ 12%|#1 | 5.33M/44.7M [00:00<00:01, 27.3MB/s]
+ 18%|#7 | 7.94M/44.7M [00:00<00:02, 15.0MB/s]
+ 22%|##1 | 9.78M/44.7M [00:00<00:02, 14.5MB/s]
+ 26%|##5 | 11.4M/44.7M [00:00<00:02, 14.9MB/s]
+ 31%|### | 13.8M/44.7M [00:00<00:01, 17.6MB/s]
+ 35%|###5 | 15.7M/44.7M [00:00<00:01, 16.7MB/s]
+ 39%|###8 | 17.4M/44.7M [00:01<00:01, 15.5MB/s]
+ 44%|####3 | 19.5M/44.7M [00:01<00:01, 16.9MB/s]
+ 47%|####7 | 21.2M/44.7M [00:01<00:01, 16.4MB/s]
+ 53%|#####2 | 23.5M/44.7M [00:01<00:01, 18.4MB/s]
+ 58%|#####8 | 25.9M/44.7M [00:01<00:00, 20.3MB/s]
+ 64%|######3 | 28.4M/44.7M [00:01<00:00, 21.9MB/s]
+ 68%|######8 | 30.5M/44.7M [00:01<00:00, 22.0MB/s]
+ 74%|#######3 | 32.9M/44.7M [00:01<00:00, 22.6MB/s]
+ 78%|#######8 | 35.0M/44.7M [00:01<00:00, 22.0MB/s]
+ 83%|########3 | 37.2M/44.7M [00:02<00:00, 20.3MB/s]
+ 89%|########8 | 39.6M/44.7M [00:02<00:00, 21.8MB/s]
+ 93%|#########3| 41.7M/44.7M [00:02<00:00, 19.7MB/s]
+ 98%|#########7| 43.7M/44.7M [00:02<00:00, 18.0MB/s]
+100%|##########| 44.7M/44.7M [00:02<00:00, 18.5MB/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 0613f676e..fd27e1849 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.238 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.916 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 a719bd1e6..82f6bb7f5 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>05:32.910</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:34.448</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:11.807</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>01:03.238</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>00:55.430</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>00:35.096</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>00:25.403</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>00:22.619</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>00:21.671</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>00:21.390</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>00:13.578</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>00:02.679</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>01:10.337</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>01:05.135</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>01:01.916</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>00:32.853</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>00:25.305</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>00:20.863</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>00:20.822</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>00:20.801</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>00:13.646</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>00:02.769</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 0c368db63..b02c131f9 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.5388 15.5206 15.6660 15.4596 0.0746
+ 16.3223 16.5146 17.0414 15.5324 0.5463
</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 6fe0ceb71..9265e7b47 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,102 +409,16 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 1%| | 0.99M/170M [00:00<00:17, 9.93MB/s]
- 1%|1 | 2.41M/170M [00:00<00:13, 12.7MB/s]
- 2%|2 | 3.63M/170M [00:00<00:16, 10.8MB/s]
- 3%|3 | 5.10M/170M [00:00<00:14, 12.2MB/s]
- 4%|3 | 6.29M/170M [00:00<00:15, 11.4MB/s]
- 5%|4 | 8.35M/170M [00:00<00:11, 14.4MB/s]
- 6%|6 | 10.6M/170M [00:00<00:09, 17.2MB/s]
- 7%|7 | 12.3M/170M [00:00<00:10, 16.0MB/s]
- 8%|8 | 13.9M/170M [00:01<00:11, 14.6MB/s]
- 9%|9 | 15.3M/170M [00:01<00:11, 14.0MB/s]
- 10%|9 | 16.7M/170M [00:01<00:13, 11.9MB/s]
- 11%|# | 18.4M/170M [00:01<00:12, 13.2MB/s]
- 13%|#3 | 22.3M/170M [00:01<00:07, 20.1MB/s]
- 14%|#4 | 24.4M/170M [00:01<00:07, 20.5MB/s]
- 16%|#5 | 26.4M/170M [00:01<00:08, 17.7MB/s]
- 17%|#6 | 28.3M/170M [00:01<00:08, 17.2MB/s]
- 18%|#7 | 30.1M/170M [00:02<00:09, 16.3MB/s]
- 19%|#8 | 32.1M/170M [00:02<00:08, 17.4MB/s]
- 20%|#9 | 33.8M/170M [00:02<00:09, 14.7MB/s]
- 21%|## | 35.3M/170M [00:02<00:11, 12.8MB/s]
- 22%|##1 | 36.6M/170M [00:02<00:11, 12.5MB/s]
- 22%|##2 | 37.9M/170M [00:02<00:11, 11.7MB/s]
- 23%|##3 | 39.5M/170M [00:02<00:10, 12.9MB/s]
- 24%|##4 | 41.3M/170M [00:02<00:09, 14.3MB/s]
- 25%|##5 | 42.8M/170M [00:03<00:10, 12.7MB/s]
- 26%|##6 | 44.5M/170M [00:03<00:09, 14.0MB/s]
- 27%|##7 | 45.9M/170M [00:03<00:09, 13.6MB/s]
- 28%|##8 | 47.7M/170M [00:03<00:08, 14.9MB/s]
- 29%|##9 | 49.5M/170M [00:03<00:07, 15.8MB/s]
- 30%|### | 51.1M/170M [00:03<00:08, 15.0MB/s]
- 31%|### | 52.5M/170M [00:03<00:08, 15.1MB/s]
- 32%|###1 | 54.1M/170M [00:03<00:07, 15.3MB/s]
- 33%|###2 | 55.6M/170M [00:03<00:07, 15.6MB/s]
- 34%|###3 | 57.2M/170M [00:04<00:07, 15.1MB/s]
- 35%|###4 | 59.1M/170M [00:04<00:07, 16.3MB/s]
- 36%|###6 | 61.2M/170M [00:04<00:06, 17.6MB/s]
- 37%|###7 | 62.9M/170M [00:04<00:06, 16.0MB/s]
- 38%|###7 | 64.5M/170M [00:04<00:07, 14.5MB/s]
- 39%|###9 | 67.0M/170M [00:04<00:06, 17.5MB/s]
- 41%|#### | 69.0M/170M [00:04<00:05, 18.2MB/s]
- 42%|####2 | 71.6M/170M [00:04<00:04, 20.7MB/s]
- 43%|####3 | 73.7M/170M [00:05<00:05, 19.7MB/s]
- 45%|####4 | 75.6M/170M [00:05<00:05, 16.8MB/s]
- 46%|####6 | 78.2M/170M [00:05<00:04, 19.5MB/s]
- 47%|####7 | 80.2M/170M [00:05<00:04, 18.9MB/s]
- 48%|####8 | 82.1M/170M [00:05<00:05, 18.1MB/s]
- 49%|####9 | 83.9M/170M [00:05<00:05, 18.0MB/s]
- 50%|##### | 85.7M/170M [00:05<00:05, 15.7MB/s]
- 51%|#####1 | 87.2M/170M [00:05<00:05, 15.1MB/s]
- 52%|#####2 | 88.7M/170M [00:06<00:06, 13.6MB/s]
- 53%|#####3 | 90.1M/170M [00:06<00:06, 13.6MB/s]
- 54%|#####3 | 91.7M/170M [00:06<00:05, 14.3MB/s]
- 55%|#####4 | 93.1M/170M [00:06<00:05, 13.6MB/s]
- 56%|#####5 | 94.8M/170M [00:06<00:05, 14.6MB/s]
- 57%|#####6 | 96.5M/170M [00:06<00:04, 15.4MB/s]
- 58%|#####7 | 98.3M/170M [00:06<00:04, 16.2MB/s]
- 59%|#####8 | 99.9M/170M [00:06<00:05, 14.2MB/s]
- 60%|#####9 | 102M/170M [00:06<00:04, 15.7MB/s]
- 61%|###### | 103M/170M [00:07<00:05, 12.7MB/s]
- 62%|######2 | 105M/170M [00:07<00:04, 14.4MB/s]
- 63%|######2 | 107M/170M [00:07<00:05, 12.5MB/s]
- 64%|######4 | 109M/170M [00:07<00:04, 14.3MB/s]
- 65%|######4 | 110M/170M [00:07<00:04, 14.4MB/s]
- 66%|######6 | 112M/170M [00:07<00:03, 15.8MB/s]
- 67%|######7 | 114M/170M [00:07<00:03, 16.0MB/s]
- 68%|######8 | 116M/170M [00:07<00:03, 16.5MB/s]
- 69%|######9 | 117M/170M [00:08<00:03, 15.3MB/s]
- 70%|######9 | 119M/170M [00:08<00:03, 15.6MB/s]
- 71%|####### | 120M/170M [00:08<00:03, 15.6MB/s]
- 72%|#######1 | 122M/170M [00:08<00:03, 15.9MB/s]
- 73%|#######2 | 124M/170M [00:08<00:03, 16.1MB/s]
- 74%|#######4 | 126M/170M [00:08<00:02, 17.2MB/s]
- 75%|#######5 | 127M/170M [00:08<00:02, 15.0MB/s]
- 76%|#######5 | 129M/170M [00:08<00:02, 15.2MB/s]
- 77%|#######6 | 130M/170M [00:09<00:03, 11.3MB/s]
- 78%|#######7 | 132M/170M [00:09<00:03, 12.5MB/s]
- 79%|#######8 | 134M/170M [00:09<00:02, 14.5MB/s]
- 80%|######## | 136M/170M [00:09<00:02, 16.0MB/s]
- 81%|########1 | 138M/170M [00:09<00:02, 15.5MB/s]
- 82%|########2 | 140M/170M [00:09<00:01, 16.9MB/s]
- 83%|########3 | 142M/170M [00:09<00:01, 15.6MB/s]
- 84%|########4 | 143M/170M [00:09<00:01, 15.6MB/s]
- 85%|########5 | 145M/170M [00:10<00:02, 13.0MB/s]
- 87%|########6 | 147M/170M [00:10<00:01, 15.8MB/s]
- 88%|########7 | 149M/170M [00:10<00:01, 17.1MB/s]
- 89%|########8 | 151M/170M [00:10<00:01, 13.0MB/s]
- 90%|########9 | 152M/170M [00:10<00:01, 14.2MB/s]
- 91%|######### | 154M/170M [00:10<00:01, 15.2MB/s]
- 92%|#########1| 156M/170M [00:10<00:01, 13.7MB/s]
- 93%|#########2| 158M/170M [00:10<00:00, 14.7MB/s]
- 94%|#########3| 159M/170M [00:11<00:00, 13.5MB/s]
- 95%|#########5| 162M/170M [00:11<00:00, 16.3MB/s]
- 97%|#########6| 164M/170M [00:11<00:00, 19.4MB/s]
- 98%|#########8| 167M/170M [00:11<00:00, 21.5MB/s]
-100%|#########9| 169M/170M [00:11<00:00, 20.4MB/s]
-100%|##########| 170M/170M [00:11<00:00, 15.4MB/s]
+ 7%|6 | 11.2M/170M [00:00<00:01, 117MB/s]
+ 16%|#6 | 27.7M/170M [00:00<00:00, 150MB/s]
+ 28%|##7 | 47.3M/170M [00:00<00:00, 176MB/s]
+ 39%|###9 | 66.7M/170M [00:00<00:00, 186MB/s]
+ 50%|##### | 85.2M/170M [00:00<00:00, 189MB/s]
+ 61%|###### | 103M/170M [00:00<00:00, 188MB/s]
+ 71%|#######1 | 121M/170M [00:00<00:00, 184MB/s]
+ 83%|########2 | 140M/170M [00:00<00:00, 189MB/s]
+ 95%|#########4| 161M/170M [00:00<00:00, 198MB/s]
+100%|##########| 170M/170M [00:00<00:00, 188MB/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').
@@ -597,7 +511,7 @@ 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 9.500 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.258 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 17b41332a..7a746f37d 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,16 +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]
- 7%|7 | 1.01M/13.6M [00:00<00:01, 10.3MB/s]
- 16%|#6 | 2.19M/13.6M [00:00<00:01, 11.4MB/s]
- 28%|##8 | 3.85M/13.6M [00:00<00:00, 14.1MB/s]
- 38%|###8 | 5.20M/13.6M [00:00<00:00, 10.7MB/s]
- 50%|####9 | 6.75M/13.6M [00:00<00:00, 11.7MB/s]
- 59%|#####8 | 7.94M/13.6M [00:00<00:00, 11.3MB/s]
- 71%|####### | 9.59M/13.6M [00:00<00:00, 12.9MB/s]
- 80%|######## | 10.9M/13.6M [00:00<00:00, 11.8MB/s]
- 89%|########9 | 12.1M/13.6M [00:01<00:00, 12.0MB/s]
-100%|##########| 13.6M/13.6M [00:01<00:00, 12.2MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 166MB/s]
</pre></div>
</div>
</div>
@@ -548,7 +539,7 @@ 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)
- 90.0302 89.9670 91.2822 89.8079 0.2209
+ 90.4680 90.1832 97.7253 90.0221 1.0371
</pre></div>
</div>
<div class="admonition note">
@@ -587,7 +578,7 @@ 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 4.515 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.301 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 e542ab273..dafa6990b 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ 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)
- 118.0240 117.8995 122.2729 116.1341 0.9010
+ 120.0440 120.0160 121.2119 119.2960 0.3302
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ 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 52.119 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.165 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 099ec8502..1ea2eeb82 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ 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 36.736 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.472 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 63b92ef3f..9950f902e 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,23 +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]
- 5%|4 | 6368/132723 [00:00<00:01, 63672.32KB/s]
- 11%|#1 | 14897/132723 [00:00<00:01, 76385.98KB/s]
- 18%|#7 | 23479/132723 [00:00<00:01, 80689.22KB/s]
- 24%|##4 | 32087/132723 [00:00<00:01, 82814.23KB/s]
- 31%|### | 40770/132723 [00:00<00:01, 84259.53KB/s]
- 37%|###7 | 49384/132723 [00:00<00:00, 84894.82KB/s]
- 44%|####3 | 57945/132723 [00:00<00:00, 85125.32KB/s]
- 50%|##### | 66458/132723 [00:00<00:00, 71183.84KB/s]
- 56%|#####5 | 73939/132723 [00:01<00:00, 60487.81KB/s]
- 61%|###### | 80456/132723 [00:01<00:00, 60996.03KB/s]
- 67%|######6 | 88391/132723 [00:01<00:00, 65757.99KB/s]
- 73%|#######3 | 96963/132723 [00:01<00:00, 71150.09KB/s]
- 80%|#######9 | 105644/132723 [00:01<00:00, 75512.47KB/s]
- 86%|########6 | 114291/132723 [00:01<00:00, 78627.39KB/s]
- 93%|#########2| 122937/132723 [00:01<00:00, 80888.66KB/s]
- 99%|#########9| 131597/132723 [00:01<00:00, 82556.80KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 75800.40KB/s]
+ 5%|5 | 7038/132723 [00:00<00:01, 70372.85KB/s]
+ 12%|#1 | 15728/132723 [00:00<00:01, 80087.83KB/s]
+ 18%|#8 | 24457/132723 [00:00<00:01, 83372.68KB/s]
+ 25%|##5 | 33229/132723 [00:00<00:01, 85082.70KB/s]
+ 32%|###1 | 41964/132723 [00:00<00:01, 85896.06KB/s]
+ 38%|###8 | 50713/132723 [00:00<00:00, 86435.80KB/s]
+ 45%|####4 | 59409/132723 [00:00<00:00, 86605.17KB/s]
+ 51%|#####1 | 68157/132723 [00:00<00:00, 86880.58KB/s]
+ 58%|#####7 | 76879/132723 [00:00<00:00, 86983.59KB/s]
+ 65%|######4 | 85619/132723 [00:01<00:00, 87109.21KB/s]
+ 71%|#######1 | 94397/132723 [00:01<00:00, 87310.19KB/s]
+ 78%|#######7 | 103170/132723 [00:01<00:00, 87434.62KB/s]
+ 84%|########4 | 111917/132723 [00:01<00:00, 87442.77KB/s]
+ 91%|######### | 120662/132723 [00:01<00:00, 87398.53KB/s]
+ 97%|#########7| 129402/132723 [00:01<00:00, 83114.54KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 84019.88KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -471,7 +470,7 @@ 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 19.867 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.377 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 d31484618..09b6209da 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>10:52.604</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:20.622</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:09.500</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>02:19.867</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>01:52.119</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>01:36.736</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>01:04.515</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>00:28.540</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>00:21.137</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>00:00.190</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>03:02.258</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>02:20.377</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>01:53.165</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>01:11.472</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>01:04.301</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>00:27.587</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>00:21.262</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>00:00.199</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 9b2fe06d6..b2571309f 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ 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.zipebb22811-12a9-49a8-a8d7-800ae10725cb 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.zip3f62893c-5c0e-48cc-a767-86f9621823b2 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>
@@ -650,7 +650,7 @@ 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>Check failed: (lower) is false: Intrinsic lowering function for target llvm, intrinsic name tir.sqrt, type 150 not found
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Check failed: (lower) is false: FloatImm lowering function for target llvm type 150 not found
</pre></div>
</div>
<p>When we attempt to run the model, we get a familiar error telling us that more functions need to be registerd for myfloat.</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index ec54ba485..d50172710 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>00:39.769</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.938</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:36.149</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>00:02.336</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>00:01.084</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>00:00.200</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>00:34.480</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>00:02.227</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>00:01.032</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>00:00.199</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 0d839be3a..19edcbccb 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: 6301us [6301us] (45.44%; 45.44%)
-FoldScaleAxis: 7566us [2us] (54.56%; 54.56%)
- FoldConstant: 7564us [1556us] (54.55%; 99.97%)
- InferType: 6008us [6008us] (43.33%; 79.43%)
+InferType: 6000us [6000us] (45.43%; 45.43%)
+FoldScaleAxis: 7207us [2us] (54.57%; 54.57%)
+ FoldConstant: 7205us [1490us] (54.56%; 99.97%)
+ InferType: 5716us [5716us] (43.28%; 79.33%)
</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: 6063us [6063us] (44.71%; 44.71%)
-FoldScaleAxis: 7497us [2us] (55.29%; 55.29%)
- FoldConstant: 7495us [1531us] (55.27%; 99.97%)
- InferType: 5964us [5964us] (43.98%; 79.57%)
+InferType: 6149us [6149us] (45.55%; 45.55%)
+FoldScaleAxis: 7351us [2us] (54.45%; 54.45%)
+ FoldConstant: 7349us [1585us] (54.44%; 99.97%)
+ InferType: 5764us [5764us] (42.70%; 78.43%)
</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 b9244590d..6fbb9871d 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: 47.082751 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 38.570183 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 5a5f9547b..869924745 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: 6.855349 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.684747 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 0910e26c2..73dd7ba9a 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: 0.018223
-Baseline: 3.524503
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018026
+Baseline: 3.275190
</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: 0.297080
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300694
</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: 0.328934
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.329160
</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: 0.114862
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117921
</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: 0.111236
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112021
</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: 0.111643
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111304
</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: 0.144929
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144713
</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 bbfbc43ce..1117744b7 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>00:35.179</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.494</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.555</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>00:01.396</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>00:31.832</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>00:01.448</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>00:01.215</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 6e7e3eaac..839e97016 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>05:02.667</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>04:58.076</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:27.183</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>01:20.913</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>00:40.029</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>00:17.815</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>00:08.462</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>00:08.266</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>02:26.085</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>01:19.147</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>00:40.043</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>00:15.871</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>00:08.535</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>00:08.395</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 537ca496c..e7a05f664 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
@@ -470,97 +470,1351 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 56;
allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [504]), 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" = 112 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[8] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [4608]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[10] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[12] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[7] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[11] = 0f32
conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
- for (rx.outer.outer: int32, 0, 3) {
- let cse_var_2: int32 = (rc.outer.outer*392)
- let cse_var_1: int32 = (rc.outer.outer*72)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [504], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((7 <= floormod(threadIdx.x_1, 63)) && (floormod(threadIdx.x_1, 63) < 56)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 63)*49)) + rx.outer.outer) + floormod(threadIdx.x_1, 63)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 7), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 7), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 16), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 7), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 5), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 5), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 32), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 5), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 7) + 3), 9)) && (floormod((floordiv(threadIdx.x_1, 7) + 3), 9) < 8)) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 48), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 3), 9)*7)) + rx.outer.outer) + floormod(th [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else((((floormod((floordiv(threadIdx.x_1, 7) + 1), 9) < 8) && (1 <= (rx.outer.outer + floormod(threadIdx.x_1, 7)))) && ((rx.outer.outer + floormod(threadIdx.x_1, 7)) < 8)), data[(((((cse_var_2 + (floordiv((floordiv(threadIdx.x_1, 7) + 64), 9)*49)) + (floormod((floordiv(threadIdx.x_1, 7) + 1), 9)*7)) + rx.outer.outer) + floormod(threadIdx.x_1, 7)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 24)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 14), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer) + 64512)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 16), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 8) + 70), 3)*4608)) + cse_var_1) + (floormod((threadIdx.x_2 + 8), 24)*3)) + rx.outer.outer)]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 112;
- if @tir.likely((threadIdx.x_2 < 96), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((blockIdx.x*147456) + (floordiv(floordiv(threadIdx.x_2, 8), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 24)*3)) + rx.outer.outer) + 129024)]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ry.outer.inner: int32, 0, 3) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 7)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 70)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 14)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 77)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 21)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 84)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 35)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 98)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 42)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 3)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[((((rc.outer.inner*126) + (ry.outer.inner*7)) + floormod(threadIdx.x, 7)) + 105)]*kernel.shared_1[((((floordiv(threadIdx.x, 7)*48) + (rc.outer.inner*6)) + ry.outer.inner) + 27)]))
- }
- }
+ let cse_var_2: int32 = (rc.outer.outer*392)
+ let cse_var_1: int32 = (rc.outer.outer*72)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod(threadIdx.x_1, 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((((cse_var_2 + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1 [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 32), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 32), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 9)*7)) + (floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 64), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 9)*7)) + (floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 96), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 96), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 96), 27), 9)*7)) + (floormo [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 128), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 128), 27), 9)*7)) + (fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ pad_temp.shared_1[(threadIdx.x_1 + 160)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 160), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 160), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 160), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 160), 27), 9)*7)) + (fl [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ if @tir.likely((threadIdx.x_1 < 24), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 192)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7))) && ((floordiv(floormod((threadIdx.x_1 + 192), 27), 9) + floormod(blockIdx.x, 7)) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 192), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 192), 27), 9)*7)) + ( [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [4608], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + (threadIdx.x_2 + 32))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 292), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 296), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 300), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 308), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 312), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 316), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 165888)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 328), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 332), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 340), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 344), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 348), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 356), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 184320)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 364), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 372), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 376), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 380), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3104)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 388), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3136)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 392), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3168)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 202752)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3232)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 404), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3264)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 408), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3296)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 412), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3360)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 420), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3392)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 424), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3424)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 428), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3488)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 436), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3520)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 440), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3552)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 444), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3616)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 452), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3648)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 456), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3680)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 460), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3744)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 239616)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3776)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 472), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3808)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 476), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3872)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 484), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3904)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 488), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3936)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 492), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4000)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 500), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4032)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 258048)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4064)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 508), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4128)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 516), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4160)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 520), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4192)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 524), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4256)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 532), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4288)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 536), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4320)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + cse_var_1) + threadIdx.x_2) + 276480)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4384)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 548), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4416)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 552), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4448)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 556), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 56), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4512)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 564), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 48), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4544)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 568), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 4576)] = kernel[((((floordiv(blockIdx.x, 7)*294912) + (floordiv((floordiv(threadIdx.x_2, 8) + 572), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 40), 72))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[1]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[2]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[5]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*144)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*144) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*144) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*144) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*144) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*144) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*144) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*144) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*144) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 97)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*144) + 98)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 99)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 100)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*144) + 101)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 102)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 103)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*144) + 104)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 105)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 106)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*144) + 107)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 108)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 109)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*144) + 110)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 111)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 112)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*144) + 113)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 114)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 115)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*144) + 116)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 117)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 118)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*144) + 119)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 120)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 121)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*144) + 122)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 123)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 124)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*144) + 125)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 126)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 127)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*144) + 128)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 129)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 130)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*144) + 131)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 132)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 133)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*144) + 134)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 135)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 136)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*144) + 137)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 138)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 139)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*144) + 140)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 141)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 142)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*144) + 143)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*144) + 143)]))
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7))] = max((conv2d_nchw_1[i1.inner] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 1)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 2)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 3)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 4)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 5)] = max((conv2d_nchw_1[(i1.inner + 10)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*3136) + (threadIdx.x*98)) + (i1.inner*49)) + (floormod(blockIdx.x, 7)*7)) + 6)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((floordiv(blockIdx.x, 7)*64) + (threadIdx.x*2)) + i1.inner)]), 0f32)
}
}
}
@@ -598,7 +1852,7 @@ 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: 0.413 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.257 ms
</pre></div>
</div>
</div>
@@ -628,37 +1882,37 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+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=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_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_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
-conv2d_nchw_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=3)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
+conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=7)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
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=16)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
-compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
+compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=7)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
kernel_shared = s.cache_read(kernel, "shared", [conv2d_nchw])
@@ -677,14 +1931,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=112)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 64)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -702,82 +1956,1197 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(112) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[14];
- __shared__ float pad_temp_shared[504];
- __shared__ float kernel_shared[768];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[4608];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
- for (int rx_outer_outer = 0; rx_outer_outer < 3; ++rx_outer_outer) {
- __syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((7 <= (((int)threadIdx.x) % 63)) && ((((int)threadIdx.x) % 63) < 56)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[(((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 63) * 49)) + rx_outer_outer) + (((int)threadIdx.x) % 63)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((1 <= (((((int)threadIdx.x) / 7) + 7) % 9)) && ((((((int)threadIdx.x) / 7) + 7) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 7) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((1 <= (((((int)threadIdx.x) / 7) + 5) % 9)) && ((((((int)threadIdx.x) / 7) + 5) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 5) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((((1 <= (((((int)threadIdx.x) / 7) + 3) % 9)) && ((((((int)threadIdx.x) / 7) + 3) % 9) < 8)) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 63) * 49)) + ((((((int)threadIdx.x) / 7) + 3) % 9) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 448)] = ((((((int)threadIdx.x) < 49) && (1 <= (rx_outer_outer + (((int)threadIdx.x) % 7)))) && ((rx_outer_outer + (((int)threadIdx.x) % 7)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 63) * 49)) + (((((int)threadIdx.x) / 7) + 1) * 7)) + rx_outer_outer) + (((int)threadIdx.x) % 7)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 112) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 224) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 336)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer) + 64512)];
- kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 448) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 16) % 24) * 3)) + rx_outer_outer)];
- kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 560) / 24) * 4608)) + (rc_outer_outer * 72)) + (((((int)threadIdx.x) + 8) % 24) * 3)) + rx_outer_outer)];
- if (((int)threadIdx.x) < 96) {
- kernel_shared[(((int)threadIdx.x) + 672)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 24) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 24) * 3)) + rx_outer_outer) + 129024)];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 7)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 70)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 14)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 77)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 21)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 84)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 35)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 98)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 42)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 3)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[((((rc_outer_inner * 126) + (ry_outer_inner * 7)) + (((int)threadIdx.x) % 7)) + 105)] * kernel_shared[(((((((int)threadIdx.x) / 7) * 48) + (rc_outer_inner * 6)) + ry_outer_inner) + 27)]));
- }
- }
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7))) && ((((((int)threadIdx.x) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((((1 <= ((((((int)threadIdx.x) + 5) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 5) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int)thr [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = (((((1 <= ((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 10) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = (((((1 <= ((((((int)threadIdx.x) + 15) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 15) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 96) / 27) * 49)) + ((((((int)threadIdx.x) + 15) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((1 <= ((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 20) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
+ pad_temp_shared[(((int)threadIdx.x) + 160)] = (((((1 <= ((((((int)threadIdx.x) + 25) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 25) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 160) / 27) * 49)) + ((((((int)threadIdx.x) + 25) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((in [...]
+ if (((int)threadIdx.x) < 24) {
+ pad_temp_shared[(((int)threadIdx.x) + 192)] = (((((1 <= ((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7))) && (((((((int)threadIdx.x) + 3) % 27) / 9) + (((int)blockIdx.x) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 192) / 27) * 49)) + ((((((int)threadIdx.x) + 3) % 27) / 9) * 7)) + ((((int)blockIdx.x) % 7) * 7)) + ((((int [...]
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 32)];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 64) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 96) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 160) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 224) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 320) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 416) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 448) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 608) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 672) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 736) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 800) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 832) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 928) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 960) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1056) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1088) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1120) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1184) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1216) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1248) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1312) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1344) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1376) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1472) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1600) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1696) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1760) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1824) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1856) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1888) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1952) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 1984) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2080) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2112) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2208) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2240) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2272) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2336) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2368) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2400) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2464) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2496) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2528) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 165888)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2624) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2720) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2752) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2848) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 184320)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2912) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 2976) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3008) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3040) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3104)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3104) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3136)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3136) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3168)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 202752)];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3232)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3232) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3264)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3264) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3296)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3360)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3360) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3392)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3392) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3424)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3424) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3488)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3488) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3520)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3520) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3552)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3552) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3616)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3616) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3648)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3648) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3680)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3680) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 3744)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 239616)];
+ kernel_shared[(((int)threadIdx.x) + 3776)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3776) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 3808)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 3872)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3872) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3904)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3904) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 3936)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4000)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4000) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 4032)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 258048)];
+ kernel_shared[(((int)threadIdx.x) + 4064)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4064) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4128)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4128) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 4160)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4160) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4192)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4192) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4256)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4256) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4288)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4288) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ kernel_shared[(((int)threadIdx.x) + 4320)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (rc_outer_outer * 72)) + ((int)threadIdx.x)) + 276480)];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 32))];
+ kernel_shared[(((int)threadIdx.x) + 4384)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 64) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4416)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4416) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 24))];
+ kernel_shared[(((int)threadIdx.x) + 4448)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 56) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 4512)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 48) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4544)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4544) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 4576)] = kernel[(((((((int)blockIdx.x) / 7) * 294912) + (((((int)threadIdx.x) + 4576) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) + 40))];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[1] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[2] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[5] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 144)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 144) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 144) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 144) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 144) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 144) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 144) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 144) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 144) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 97)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 144) + 98)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 99)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 100)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 144) + 101)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 102)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 103)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 144) + 104)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 105)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 106)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 144) + 107)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 108)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 109)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 144) + 110)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 111)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 112)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 144) + 113)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 114)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 115)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 144) + 116)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 117)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 118)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 144) + 119)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 120)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 121)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 144) + 122)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 123)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 124)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 144) + 125)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 126)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 127)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 144) + 128)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 129)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 130)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 144) + 131)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 132)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 133)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 144) + 134)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 135)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 136)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 144) + 137)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 138)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 139)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 144) + 140)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 141)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 142)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 144) + 143)]));
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[(((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7))] = max((conv2d_nchw[i1_inner] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 1)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 2)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 3)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 4)] = max((conv2d_nchw[(i1_inner + 8)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 5)] = max((conv2d_nchw[(i1_inner + 10)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 3136) + (((int)threadIdx.x) * 98)) + (i1_inner * 49)) + ((((int)blockIdx.x) % 7) * 7)) + 6)] = max((conv2d_nchw[(i1_inner + 12)] + bias[((((((int)blockIdx.x) / 7) * 64) + (((int)threadIdx.x) * 2)) + i1_inner)]), 0.000000e+00f);
}
}
</pre></div>
@@ -815,7 +3184,7 @@ 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 27.183 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 26.085 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 521126505..005e65972 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ 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)
- 9.9670 9.9606 10.0306 9.9100 0.0494
+ 9.5660 9.5569 9.5919 9.5492 0.0186
</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 a5c123190..6101842d2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ 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)
- 755.3439 753.5566 759.6341 752.8411 3.0476
+ 752.9251 750.6992 759.9661 748.1100 5.0897
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ 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 20.913 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.147 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 572a50511..f6b262aac 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,28 +600,76 @@ 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], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
- for (i.outer.inner: int32, 0, 8) {
+ preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 512) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
for (i.inner.init: int32, 0, 4) {
- for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*64) + (i.inner.init*16)) + j.init)] = 0f32
+ let cse_var_1: int32 = ((i.outer.inner*64) + (i.inner.init*16))
+ {
+ compute_5: Buffer(compute_4, float32, [128], [])[cse_var_1] = 0f32
+ compute_5[(cse_var_1 + 1)] = 0f32
+ compute_5[(cse_var_1 + 2)] = 0f32
+ compute_5[(cse_var_1 + 3)] = 0f32
+ compute_5[(cse_var_1 + 4)] = 0f32
+ compute_5[(cse_var_1 + 5)] = 0f32
+ compute_5[(cse_var_1 + 6)] = 0f32
+ compute_5[(cse_var_1 + 7)] = 0f32
+ compute_5[(cse_var_1 + 8)] = 0f32
+ compute_5[(cse_var_1 + 9)] = 0f32
+ compute_5[(cse_var_1 + 10)] = 0f32
+ compute_5[(cse_var_1 + 11)] = 0f32
+ compute_5[(cse_var_1 + 12)] = 0f32
+ compute_5[(cse_var_1 + 13)] = 0f32
+ compute_5[(cse_var_1 + 14)] = 0f32
+ compute_5[(cse_var_1 + 15)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (elem_idx: int32, 0, let cse_var_2: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
for (i.inner: int32, 0, 4) {
- 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*64) + (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)*8192) + (i.outer.inner*1024)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ let cse_var_21: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_20: int32 = (elem_idx*16)
+ let cse_var_19: int32 = ((i.outer.inner*64) + (i.inner*16))
+ let cse_var_18: int32 = (cse_var_19 + 10)
+ let cse_var_17: int32 = (cse_var_19 + 11)
+ let cse_var_16: int32 = (cse_var_19 + 12)
+ let cse_var_15: int32 = (cse_var_19 + 13)
+ let cse_var_14: int32 = (cse_var_19 + 14)
+ let cse_var_13: int32 = (cse_var_19 + 15)
+ let cse_var_12: int32 = (cse_var_19 + 2)
+ let cse_var_11: int32 = (cse_var_19 + 3)
+ let cse_var_10: int32 = (cse_var_19 + 4)
+ let cse_var_9: int32 = (cse_var_19 + 5)
+ let cse_var_8: int32 = (cse_var_19 + 6)
+ let cse_var_7: int32 = (cse_var_19 + 7)
+ let cse_var_6: int32 = (cse_var_19 + 8)
+ let cse_var_5: int32 = (cse_var_19 + 9)
+ let cse_var_4: int32 = (cse_var_19 + 1)
+ let cse_var_3: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*2048) + (i.outer.inner*1024)) + (i.inner*256))
+ {
+ compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_21]*16) + cse_var_20)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 1)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 2)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 3)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 4)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 5)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 6)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 7)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 8)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 9)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 10)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 11)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 12)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 13)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 14)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_21]*16) + cse_var_20) + 15)]*max(placeholder[(cse_var_3 + placeholder_2[(placeholder_3[cse_var_21] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
- compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 8) {
+ let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_22, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_22, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -660,7 +708,7 @@ 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: 1.474 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.828 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 e28f359c5..3ccbbbe89 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>00:44.195</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.482</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:43.373</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>00:00.217</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>00:00.205</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>00:00.200</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>00:00.200</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>00:43.622</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>00:00.223</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>00:00.217</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>00:00.211</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_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>
</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 5feb8f9e3..c93c59196 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: 102.59/102.59 result: MeasureResult(costs=(0.0022566282291666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5949983596801758, timestamp=1650690027.666691) [('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: 0.00/102.59 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.50/42.50 result: MeasureResult(costs=(0.005446518210526316,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5788905620574951, timestamp=1650788920.652944) [('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: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.50 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: 0.00/102.59 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.50 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: 0.00/102.59 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.50 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: 0x00007f48339cefa2
+ 12: 0x00007fdcf9cebfa2
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: 142.38/142.38 result: MeasureResult(costs=(0.0016259662,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.420372486114502, timestamp=1650690054.0953064) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
+No: 20 GFLOPS: 144.45/144.45 result: MeasureResult(costs=(0.00160269044,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4209423065185547, timestamp=1650788946.9838886) [('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: 0.001982
+Time cost of this operator: 0.002066
</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 12d150c80..8df77ac52 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.8 98.738 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.97 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.292 (1, 1, 10, 10, 3) 1 1
-Total_time - 316.798 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.6 98.768 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.945 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.913 0.287 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.513 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ 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 81.0 96.817 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.728 2.065 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.936 1.118 (1, 1, 10, 10, 3) 1 1
-Total_time - 83.663 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 81.8 96.81 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.772 2.097 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.924 1.093 (1, 1, 10, 10, 3) 1 1
+Total_time - 84.496 - - - -
</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 c97d5519e..263d589c6 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>00:44.000</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:43.859</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:39.918</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>00:03.494</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>00:00.208</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>00:00.191</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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
-<li><p><strong>00:00.190</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>00:39.815</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>00:03.447</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>00:00.203</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</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
+<li><p><strong>00:00.201</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>00:00.192</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 1a9ac2fa3..2eff971a5 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>00:09.154</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:08.880</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:07.437</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>00:01.503</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>00:00.214</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>00:06.841</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>00:01.817</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>00:00.222</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 e3c17b1d3..91be62492 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>00:05.549</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.541</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.037</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>00:01.145</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>00:00.713</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>00:00.690</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>00:00.298</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>00:00.227</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>00:00.224</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>00:00.217</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>00:02.058</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>00:01.087</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>00:00.721</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>00:00.703</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>00:00.296</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>00:00.241</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>00:00.224</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>00:00.211</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 f2b86b104..fdb482632 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/tmp6yusbrem/input0.cc'\nsource_filename = \"/tmp/tmp6yusbrem/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/tmpqk99po7x/input0.cc'\nsource_filename = \"/tmp/tmpqk99po7x/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index a9484c274..e5f516caf 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1713,7 +1713,7 @@ 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">
@@ -1750,7 +1750,7 @@ 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 9f39b7893..634dac508 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/bce57586b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 79c6b638c..7917bb163 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/bce57586b/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 629532ede..816cea7c0 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/bce57586b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 382b466cf..1f0288b47 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/bce57586b/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 4fa2c09c3..a9110aef5 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/bce57586b/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 808a39a31..3cae4f981 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/bce57586b/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 71fa1e9f4..23dffb533 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/bce57586b/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 c3b1be0d2..ddbe65fc0 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/bce57586b/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 4cd7026fc..c300956b2 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/bce57586b/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 a49e344b7..1b64a0b68 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/bce57586b/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 4fd65beb5..6f4441fe8 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/bce57586b/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 0a96b4fe3..74a1b5713 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/bce57586b/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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 ab25fdef2..65118cd36 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/bce57586b/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/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/bce57586b/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/822d86377/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
... 1587 lines suppressed ...