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 2022/06/20 14:29:24 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@8bf6cd5800daaf42935fd69cbd63180c97bef262)
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 53e10695d deploying docs (apache/tvm@8bf6cd5800daaf42935fd69cbd63180c97bef262)
53e10695d is described below
commit 53e10695dda034c12e0f3a794f42d93f65505025
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Mon Jun 20 14:29:18 2022 +0000
deploying docs (apache/tvm@8bf6cd5800daaf42935fd69cbd63180c97bef262)
---
.../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 | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1265 +++++++++++++++-----
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 133 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 7 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 20 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 129 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 9 +-
docs/how_to/compile_models/from_tensorflow.html | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 26 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 22 +-
docs/how_to/deploy_models/deploy_prequantized.html | 7 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 18 +-
.../tune_conv2d_layer_cuda.html | 1265 +++++++++++++++-----
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 133 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 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 | 3 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 260 ++--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 24 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
121 files changed, 2889 insertions(+), 1632 deletions(-)
diff --git a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
index 2edba161f..9f3fbc6cf 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1aefc1d6-d6a9-424f-87e5-0b0fcb892af8 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe51c9289-499f-45fe-8168-5039d762f3c4 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 5812b065c..8c22dc775 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ 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<05:17, 137kB/s]
0%| | 96.0k/41.5M [00:00<03:46, 192kB/s]
0%| | 160k/41.5M [00:00<02:52, 252kB/s]
1%| | 304k/41.5M [00:00<01:38, 440kB/s]
1%|1 | 608k/41.5M [00:01<00:50, 845kB/s]
3%|2 | 1.19M/41.5M [00:01<00:25, 1.64MB/s]
6%|5 | 2.30M/41.5M [00:01<00:13, 3.04MB/s]
8%|7 | 3.29M/41.5M [00:01<00:10, 3.64MB/s]
11%|#1 | 4.76M/41.5M [00:01<00:07, 4.97MB/s]
15%|#5 | 6.23M/41.5M [00:02<00:06, 5.91MB/s]
19%|#8 | 7.68M/41.5M [00:02<00:05, 6.52MB/s]
22%|##2 | 9.16M/41.5M [00:02<00:04, 7.00MB/s]
26%|##5 | 10.6M/41.5M [00:02<00:04, 7.32MB/s]
29%|##9 | 12.1M/41.5M [00:02<00:04, 7.55MB/s]
33%|###2 | 13.6M/41.5M [00:03<00:03, 7.70MB/s]
36%|###6 | 15.0M/41.5M [00:03<00
:03, 7.81MB/s]
40%|###9 | 16.5M/41.5M [00:03<00:03, 7.89MB/s]
43%|####3 | 18.0M/41.5M [00:03<00:03, 7.90MB/s]
47%|####6 | 19.4M/41.5M [00:03<00:02, 8.90MB/s]
50%|##### | 20.9M/41.5M [00:03<00:02, 9.96MB/s]
53%|#####2 | 21.9M/41.5M [00:04<00:02, 8.83MB/s]
55%|#####4 | 22.8M/41.5M [00:04<00:02, 7.68MB/s]
57%|#####7 | 23.8M/41.5M [00:04<00:02, 7.08MB/s]
61%|###### | 25.3M/41.5M [00:04<00:02, 8.35MB/s]
64%|######4 | 26.8M/41.5M [00:04<00:01, 9.45MB/s]
67%|######6 | 27.7M/41.5M [00:04<00:01, 8.52MB/s]
69%|######8 | 28.6M/41.5M [00:04<00:01, 7.36MB/s]
72%|#######1 | 29.7M/41.5M [00:05<00:01, 7.96MB/s]
75%|#######5 | 31.2M/41.5M [00:05<00:01, 9.21MB/s]
77%|#######7 | 32.1M/41.5M [00:05<00:01, 8.25MB/s]
79%|#######9 | 32.9M/41.5M [00:05<00:01, 7.11MB/s]
82%|########2 | 34.1M/41.5M [00:05<00:01, 6.94MB/s]
86%|########5 | 35.6M/41.5M [00:05<00:00, 8.51MB/s]
89%|####
####8 | 36.8M/41.5M [00:05<00:00, 9.28MB/s]
91%|######### | 37.7M/41.5M [00:06<00:00, 7.92MB/s]
93%|#########2| 38.6M/41.5M [00:06<00:00, 6.93MB/s]
96%|#########6| 40.0M/41.5M [00:06<00:00, 8.64MB/s]
99%|#########8| 40.9M/41.5M [00:06<00:00, 8.79MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 6.49MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<08:10, 88.6kB/s]
0%| | 40.0k/41.5M [00:00<06:27, 112kB/s]
0%| | 64.0k/41.5M [00:00<06:00, 120kB/s]
0%| | 96.0k/41.5M [00:00<04:56, 146kB/s]
0%| | 120k/41.5M [00:00<04:59, 145kB/s]
0%| | 152k/41.5M [00:01<04:31, 160kB/s]
0%| | 176k/41.5M [00:01<04:46, 151kB/s]
0%| | 208k/41.5M [00:01<04:35, 157kB/s]
1%| | 240k/41.5M [00:01<04:24, 164kB/s]
1%| | 280k/41.5M [00:01<03:53, 185kB/s]
1%| | 312k/41.5M [00:01<03:51, 187kB/s]
1%| | 344k/41.5M [00:02<03:50, 187kB/s]
1%| | 384k/41.5M [00:02<03:35, 200kB/s]
1%| | 424k/41.5M [00:02<03:28, 206kB/s]
1%|1 | 464k/41.5M [00:02<03:25, 210kB/s]
1%|1 | 512k/41.5M [00:02<03:11, 224kB/s]
1%|1 | 552k/41.5M [00:03<03:11, 225kB/s]
1%|1 | 600k/41.5M [00:03<02:57, 242kB/s]
2%|1 | 656k/41.5M [00:03<02:39, 268kB/s]
2%|1 | 704k/41.5M [00:03<02:36, 273kB/s]
2%|1 | 760k/41.5M [00:03<02:31, 282kB/s]
2%|1 | 816k/41.5M [00:03<02:28, 287kB/s]
2%|2 | 872k/41.5M [00:04<02:25, 293kB/s]
2%|2 | 936k/41.5M [00:04<02:13, 318kB/s]
2%|2 | 0.98M/41.5M [00:04<02:06, 336kB/s]
3%|2 | 1.05M/41.5M [00:04<01:52, 376kB/s]
3%|2 | 1.13M/41.5M [00:04<01:45, 400kB/s]
3%|2 | 1.22M/41.5M [00:05<01:39, 424kB/s]
3%|3 | 1.30M/41.5M [00:05<01:36, 438kB/s]
3%|3 | 1.41M/41.5M [00:05<01:27, 482kB/s]
4%|3 | 1.52M/41.5M [00:05<01:18, 534kB/s]
4%|3 | 1.63M/41.5M [00:05<01:11, 585kB/s]
4%|4 | 1.76M/41.5M [00:05<01:06, 631kB/s]
5%|4 | 1.90M/41.5M [00:06<01:01, 680kB/s]
5%|4 | 2.05M/41.5M [00:06<00:57, 725kB/s]
5%|5 | 2.20M/41.5M [00:06<00:53, 774kB/s]
6%|5 | 2.38M/41.5M [00:06<00:48, 851kB/s]
6%|6 | 2.56M/41.5M [00:06<00:43, 933kB/s]
7%|6 | 2.76M/41.5M [00:07<00:40, 994kB/s]
7%|7 | 2.97M/41.5M [00:07<00:38, 1.06MB/s]
8%|7 | 3.20M/41.5M [00:07<00:35, 1.12MB/s]
8%|8 | 3.43M/41.5M [00:07<00:34, 1.17MB/s]
9%|8 | 3.69M/41.5M [00:07<00:31, 1.26MB/s]
10%|9 | 3.96M/41.5M [00:07<00:28, 1.38MB/s]
10%|# | 4.26M/41.5M [00:08<00:26, 1.50MB/s]
11%|#1 | 4.57M/41.5M [00:08<00:24, 1.61MB/s]
12%|#1 | 4.90M/41.5M [00:08<00:22, 1.70MB/s]
13%|#2 | 5.25M/41.5M [00:08<00:21, 1.79MB/s]
14%|#3 | 5.61M/41.5M [00:08<00:20, 1.85MB/s]
14%|#4 | 5.99M/41.5M [00:09<00:19, 1.93MB/s]
15%|#5 | 6.41M/41.5M [00:09<00:17, 2.09MB/s]
17%|#6 | 6.85M/41.5M [00:09<00:16, 2.27MB/s]
18%|#7 | 7.31M/41.5M [
00:09<00:14, 2.42MB/s]
19%|#8 | 7.80M/41.5M [00:09<00:13, 2.55MB/s]
20%|## | 8.32M/41.5M [00:09<00:13, 2.66MB/s]
21%|##1 | 8.86M/41.5M [00:10<00:12, 2.71MB/s]
23%|##2 | 9.44M/41.5M [00:10<00:10, 3.20MB/s]
24%|##4 | 10.1M/41.5M [00:10<00:08, 3.69MB/s]
25%|##5 | 10.4M/41.5M [00:10<00:08, 3.66MB/s]
26%|##6 | 10.8M/41.5M [00:10<00:10, 3.18MB/s]
27%|##7 | 11.4M/41.5M [00:10<00:08, 3.76MB/s]
29%|##9 | 12.1M/41.5M [00:10<00:07, 3.94MB/s]
31%|### | 12.9M/41.5M [00:11<00:06, 4.81MB/s]
32%|###2 | 13.4M/41.5M [00:11<00:06, 4.23MB/s]
33%|###3 | 13.8M/41.5M [00:11<00:08, 3.61MB/s]
35%|###4 | 14.5M/41.5M [00:11<00:06, 4.34MB/s]
37%|###7 | 15.4M/41.5M [00:11<00:05, 4.64MB/s]
39%|###9 | 16.3M/41.5M [00:11<00:05, 4.94MB/s]
42%|####1 | 17.2M/41.5M [00:12<00:05, 4.48MB/s]
44%|####3 | 18.2M/41.5M [00:12<00:05, 4.78MB/s]
46%|####6 | 19.3M/41.5M [00:12<00:04, 5.81MB/s]
49%|####9 | 20.3M/41.5M [00:12<00:03, 6.92MB/s]
51%|##### | 21.1M/41.5M [00:12<00:03, 6.40MB/s]
52%|#####2 | 21.8M/41.5M [00:12<00:03, 5.69MB/s]
55%|#####4 | 22.7M/41.5M [00:13<00:03, 5.66MB/s]
58%|#####7 | 24.0M/41.5M [00:13<00:02, 6.25MB/s]
61%|###### | 25.3M/41.5M [00:13<00:02, 6.70MB/s]
64%|######4 | 26.7M/41.5M [00:13<00:02, 7.19MB/s]
68%|######7 | 28.2M/41.5M [00:13<00:01, 7.66MB/s]
71%|#######1 | 29.6M/41.5M [00:13<00:01, 7.88MB/s]
75%|#######5 | 31.1M/41.5M [00:14<00:01, 8.03MB/s]
79%|#######8 | 32.6M/41.5M [00:14<00:01, 8.23MB/s]
82%|########2 | 34.1M/41.5M [00:14<00:00, 8.33MB/s]
86%|########5 | 35.6M/41.5M [00:14<00:00, 8.31MB/s]
89%|########9 | 37.1M/41.5M [00:14<00:00, 9.61MB/s]
92%|#########2| 38.3M/41.5M [00:14<00:00, 10.4MB/s]
95%|#########5| 39.4M/41.5M [00:15<00:00, 8.94MB/s]
97%|#########7| 40.4M/41.5M
[00:15<00:00, 7.95MB/s]
100%|##########| 41.5M/41.5M [00:15<00:00, 2.85MB/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 86f25df1f..f3006b9d0 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.216 seconds)
+ **Total running time of the script:** ( 1 minutes 7.572 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 74bdc3212..9f6a9c1b4 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ 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]
23%|##2 | 10.1M/44.7M [00:00<00:00, 105MB/s]
59%|#####9 | 26.4M/44.7M [00:00<00:00, 144MB/s]
96%|#########5| 42.8M/44.7M [00:00<00:00, 157MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 150MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
18%|#8 | 8.20M/44.7M [00:00<00:00, 83.9MB/s]
36%|###6 | 16.2M/44.7M [00:00<00:00, 80.8MB/s]
66%|######6 | 29.5M/44.7M [00:00<00:00, 107MB/s]
89%|########9 | 39.8M/44.7M [00:00<00:00, 95.3MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 98.2MB/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 3416448b9..00fc31231 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -422,7 +422,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.672 seconds)
+ **Total running time of the script:** ( 1 minutes 4.589 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 e197572e5..454456088 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:33.043** total execution time for **how_to_compile_models** files:
+**05:39.340** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:08.672 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:07.572 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:08.216 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.589 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:58.153 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:59.130 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:32.464 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:41.597 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.813 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.963 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.968 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.728 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.053 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.091 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.921 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.843 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.127 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:13.447 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.657 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.380 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 46d12d688..c9d87d643 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
@@ -440,7 +440,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1979 16.1767 16.3467 16.0937 0.0742
+ 16.3130 16.2621 16.8176 16.0556 0.2160
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 6643e3bd3..ff625cc43 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
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
7%|6 | 11.5M/170M [00:00<00:01, 120MB/s]
17%|#7 | 29.4M/170M [00:00<00:00, 160MB/s]
26%|##6 | 44.7M/170M [00:00<00:00, 137MB/s]
36%|###6 | 62.0M/170M [00:00<00:00, 152MB/s]
45%|####5 | 77.3M/170M [00:00<00:00, 155MB/s]
54%|#####4 | 92.3M/170M [00:00<00:00, 143MB/s]
64%|######4 | 109M/170M [00:00<00:00, 153MB/s]
73%|#######3 | 125M/170M [00:00<00:00, 156MB/s]
82%|########2 | 140M/170M [00:00<00:00, 153MB/s]
92%|#########1| 155M/170M [00:01<00:00, 156MB/s]
100%|##########| 170M/170M [00:01<00:00, 154MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
9%|9 | 16.0M/170M [00:00<00:00, 168MB/s]
22%|##2 | 37.4M/170M [00:00<00:00, 201MB/s]
35%|###4 | 59.1M/170M [00:00<00:00, 213MB/s]
48%|####7 | 80.8M/170M [00:00<00:00, 219MB/s]
61%|###### | 103M/170M [00:00<00:00, 224MB/s]
73%|#######3 | 125M/170M [00:00<00:00, 224MB/s]
86%|########5 | 146M/170M [00:00<00:00, 224MB/s]
99%|#########8| 167M/170M [00:00<00:00, 224MB/s]
100%|##########| 170M/170M [00:00<00:00, 220MB/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').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 58.809 seconds)
+ **Total running time of the script:** ( 3 minutes 0.820 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 e222b9ddf..d14f7793c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ 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]
61%|###### | 8.21M/13.6M [00:00<00:00, 86.0MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 106MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 204MB/s]
@@ -399,7 +399,7 @@ 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)
- 90.3233 90.2573 94.0689 90.0885 0.4359
+ 90.2946 90.2761 90.7085 90.1167 0.0949
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.828 seconds)
+ **Total running time of the script:** ( 1 minutes 8.244 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 7d5ab1796..d74d3390b 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
@@ -426,7 +426,7 @@ 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)
- 120.0180 119.8968 124.4241 119.0212 0.6890
+ 121.6670 121.6092 123.9842 120.4591 0.5718
@@ -463,7 +463,7 @@ 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 52.154 seconds)
+ **Total running time of the script:** ( 1 minutes 53.431 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 ce8b22790..5b6d7755a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 16.584 seconds)
+ **Total running time of the script:** ( 1 minutes 13.142 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 b1e21662f..3b147d8d0 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
@@ -157,7 +157,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
2%|2 | 2979/132723 [00:00<00:04, 29784.06KB/s]
5%|4 | 6292/132723 [00:00<00:03, 31684.76KB/s]
9%|9 | 12387/132723 [00:00<00:02, 45029.64KB/s]
15%|#5 | 19937/132723 [00:00<00:01, 57047.30KB/s]
21%|## | 27818/132723 [00:00<00:01, 64889.36KB/s]
27%|##7 | 35946/132723 [00:00<00:01, 70459.09KB/s]
33%|###3 | 44125/132723 [00:00<00:01, 74158.71KB/s]
39%|###9 | 52342/132723 [00:00<00:01, 76707.00KB/s]
46%|####5 | 60551/132723 [00:00<00:00, 78387.93KB/s]
52%|#####1 | 68813/132723 [00:01<00:00, 79691.15KB/s]
58%|#####7 | 76964/132723 [00:01<00:00, 80244.50KB/s]
64%|######4 | 85156/132723 [00:01<00:00, 80749.43KB/s]
70%|####### | 93348/132723 [00:01<00:00, 81102.50KB/s]
76%|#######6 | 101524/132723 [00:01<00:00, 81299.17KB/s]
83%|########2 | 109738/132723 [00:01<00:00, 81548.70KB/s]
89%|########8
| 117914/132723 [00:01<00:00, 81602.36KB/s]
95%|#########4| 126075/132723 [00:01<00:00, 79626.76KB/s]
100%|##########| 132723/132723 [00:01<00:00, 74144.83KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|5 | 6665/132723 [00:00<00:01, 66641.17KB/s]
12%|#1 | 15330/132723 [00:00<00:01, 78402.88KB/s]
18%|#8 | 23909/132723 [00:00<00:01, 81773.71KB/s]
25%|##4 | 32619/132723 [00:00<00:01, 83874.15KB/s]
31%|###1 | 41325/132723 [00:00<00:01, 85019.08KB/s]
38%|###7 | 50057/132723 [00:00<00:00, 85796.22KB/s]
44%|####4 | 58824/132723 [00:00<00:00, 86400.90KB/s]
51%|##### | 67571/132723 [00:00<00:00, 86737.88KB/s]
58%|#####7 | 76351/132723 [00:00<00:00, 87066.53KB/s]
64%|######4 | 85058/132723 [00:01<00:00, 87001.55KB/s]
71%|####### | 93825/132723 [00:01<00:00, 87201.58KB/s]
77%|#######7 | 102594/132723 [00:01<00:00, 87348.41KB/s]
84%|########3 | 111417/132723 [00:01<00:00, 87612.31KB/s]
91%|######### | 120179/132723 [00:01<00:00, 87589.94KB/s]
97%|#########7| 128939/132723 [00:01<00:00, 87483.14KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 85859.92KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 23.635 seconds)
+ **Total running time of the script:** ( 2 minutes 23.969 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 d06ad6c73..eb15a9bf4 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**10:30.951** total execution time for **how_to_deploy_models** files:
+**10:32.914** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:58.809 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:00.820 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:23.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:23.969 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.154 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.431 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:16.584 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:13.142 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.828 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.244 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.742 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:30.776 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.193 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.526 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 19f537681..f901c0d81 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
@@ -463,7 +463,7 @@ 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.zipb45f2be3-2555-43eb-b14e-f49412a1b804 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip5afb26b7-b727-419c-9f87-739b3c98352b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
diff --git a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
index aeb2bdffc..ed546d984 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.436** total execution time for **how_to_extend_tvm** files:
+**00:41.438** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.237 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:38.188 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.250 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.298 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.941 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.946 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.006 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index ed8b0b543..6f00609d3 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
@@ -215,10 +215,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 7012us [7012us] (46.31%; 46.31%)
- FoldScaleAxis: 8129us [7us] (53.69%; 53.69%)
- FoldConstant: 8122us [1634us] (53.65%; 99.92%)
- InferType: 6488us [6488us] (42.85%; 79.88%)
+ InferType: 7204us [7204us] (46.14%; 46.14%)
+ FoldScaleAxis: 8410us [9us] (53.86%; 53.86%)
+ FoldConstant: 8401us [1606us] (53.80%; 99.89%)
+ InferType: 6796us [6796us] (43.52%; 80.89%)
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6628us [6628us] (44.87%; 44.87%)
- FoldScaleAxis: 8143us [6us] (55.13%; 55.13%)
- FoldConstant: 8137us [1672us] (55.09%; 99.93%)
- InferType: 6465us [6465us] (43.77%; 79.45%)
+ InferType: 6617us [6617us] (45.31%; 45.31%)
+ FoldScaleAxis: 7986us [5us] (54.69%; 54.69%)
+ FoldConstant: 7981us [1612us] (54.65%; 99.94%)
+ InferType: 6369us [6369us] (43.61%; 79.80%)
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 7cdda4d41..c17d061aa 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
@@ -327,7 +327,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.151550 ms
+ Convolution: 54.210778 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 cff7234df..27db59169 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
@@ -658,7 +658,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 7.319113 ms
+ conv2d with tensor core: 7.005482 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 19c6d6f0a..d24bcd548 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019108
- Baseline: 3.456533
+ Numpy running time: 0.019229
+ Baseline: 3.267013
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.317625
+ Opt1: 0.317688
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.344836
+ Opt2: 0.347051
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118763
+ Opt3: 0.120966
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110642
+ Opt4: 0.111611
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111169
+ Opt5: 0.111472
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145670
+ Opt6: 0.145327
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 22d1125cb..7ca195fc1 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.081** total execution time for **how_to_optimize_operators** files:
+**00:34.613** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.812 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.261 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.212 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.292 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.057 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.060 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index c4c07a96b..e647e8724 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:20.119** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:17.770** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:41.682 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:36.362 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.011 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:22.625 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.386 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.936 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:16.745 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.194 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.722 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.865 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.572 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.789 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 03c646de1..fc80c98e2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,196 +239,494 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (rc.outer.outer*288)
- let cse_var_2: int32 = (ry.outer.outer*7)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 196), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 197)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 197), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 198)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 146)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 199)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 199), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 392), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 393)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 393), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 394)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 394), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 395)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 395), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 588), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 589)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 589), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 590)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 590), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 591)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 591), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 784), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 785)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 785), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 786)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 786), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 787)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 787), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 980), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 981)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 755)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 982)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 982), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 983)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 983), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1176), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1177)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1177), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1178)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1178), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1179)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 909)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1372), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1373)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1373), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1374)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1374), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1375)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1375), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1568), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1569)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1569), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1570)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1570), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1571)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1571), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1364)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1765)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1765), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1766)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1766), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1767)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1767), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1960), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1961)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1961), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1962)] = @tir.if_then_else(((((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1518)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1963)] = @tir.if_then_else(((((floordiv(floormod(((threadIdx.x_1*4) + 1963), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1963), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 98), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 196), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 245), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 343), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 19), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 490), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 539), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 637), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 686), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 33), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 21), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_7: int32 = (ff.outer.inner*2)
- let cse_var_6: int32 = (cse_var_7 + 1)
- let cse_var_5: int32 = ((ff.outer.inner*192) + (rc.outer.inner*24))
- {
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_5]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 96)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 97)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 98)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 99)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 100)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 101)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 102)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 103)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 104)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 105)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 10)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 106)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 11)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 107)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 108)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 13)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 109)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 14)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 110)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 111)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 16)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 112)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 17)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 113)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 18)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 114)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 19)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 115)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 20)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 116)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 21)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 117)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 22)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 118)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 23)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 119)]))
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 98), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 196), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 294), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 392), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 490), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 85), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 588), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 102), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 686), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 119), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 136), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 980), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 170), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1078), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 187), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 204), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 22), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 59), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 221), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 49), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 98), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 147), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 196), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 392), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 245), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 490), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 294), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 343), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 686), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 441), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 6), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 490), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 980), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 539), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1078), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 588), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 637), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1274), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 686), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1372), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 735), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 10), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 833), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1666), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 882), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 931), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1862), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 980), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1960), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1029), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 14), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1078), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2156), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 50), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1127), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2254), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1197)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1198)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1199)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1206)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1207)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1208)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1215)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1216)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1217)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1224)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1225)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1226)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1242)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1243)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1244)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1251)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1252)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1253)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1260)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1261)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1262)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1269)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1270)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1271)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1278)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1279)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1280)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1287)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1288)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1289)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1296)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 145)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1297)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 146)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1298)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 153)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1305)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 154)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1306)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 155)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 162)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1314)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 163)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1315)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 164)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 171)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1323)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 172)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1324)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 173)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1325)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 180)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1332)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 181)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1333)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 182)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1334)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 189)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1341)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 190)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1342)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 191)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1343)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1350)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 199)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1351)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1352)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 207)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1359)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 208)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1360)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 209)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1361)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 216)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1368)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 217)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1369)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 218)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1370)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 225)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1377)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 226)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1378)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 227)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1379)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 234)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1386)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 235)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1387)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 236)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1388)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 243)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1395)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 244)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1396)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 245)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1397)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 252)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1404)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 253)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1405)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 254)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1406)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 261)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1413)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 262)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1414)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 263)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1415)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 270)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1422)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 271)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1423)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 272)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1424)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 279)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1431)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 280)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1432)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 281)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1433)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 288)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1440)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 289)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1441)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 290)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1442)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 297)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1449)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 298)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1450)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 299)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1451)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 306)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1458)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 307)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1459)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 308)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1460)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 315)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1467)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 316)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1468)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 317)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1469)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 324)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1476)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 325)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1477)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 326)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1478)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 333)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1485)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 334)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1486)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 335)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1487)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 342)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1494)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 343)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1495)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 344)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1496)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 351)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1503)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 352)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1504)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 353)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1505)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1512)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 361)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1513)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 362)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1514)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 369)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1521)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 370)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1522)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 371)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1523)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 378)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1530)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 379)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1531)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 380)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1532)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1539)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 388)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1540)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 389)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1541)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 396)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1548)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 397)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1549)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 398)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1550)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 405)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1557)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 406)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1558)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 407)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1559)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 414)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1566)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 415)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1567)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 416)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1568)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 423)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1575)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 424)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1576)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 425)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 433)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 434)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 441)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 442)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 443)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 450)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 451)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 452)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 459)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 460)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 461)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1613)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 468)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1620)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 469)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1621)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 470)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1622)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 477)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1629)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 478)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1630)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 479)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1631)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 486)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1638)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 487)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1639)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 488)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1640)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 495)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1647)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 496)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1648)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 497)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1649)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 504)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1656)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 505)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1657)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 506)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1658)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 513)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1665)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 514)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1666)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 515)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1667)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 522)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1674)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 523)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1675)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 524)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1676)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 531)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1683)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 532)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1684)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 533)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1685)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 540)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1692)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 541)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1693)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 542)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1694)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 549)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1701)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 550)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1702)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 551)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1703)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 558)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1710)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 559)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1711)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 560)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1712)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 567)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1719)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 568)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1720)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 569)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1721)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 8)]), 0f32)
}
}
}
@@ -483,7 +781,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.263 ms
+ Execution time of this operator: 0.346 ms
@@ -531,10 +829,10 @@ 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_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=4)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=2)
+ 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=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -543,19 +841,19 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
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=8)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=8)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -580,14 +878,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+ 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=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -605,148 +903,453 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[768];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 196)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 197)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 197) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 198)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 146)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 199)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 199) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 394)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 395)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 395) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 588)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 589)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 590)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 591)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 591) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 786)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 786) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 787)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 787) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 980)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 981)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 755)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 982)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 982) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 983)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 983) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1178) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1179)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 909)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1372)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1373)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1373) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1374)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1374) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1375)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1375) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1570)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1570) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1571)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1571) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1764)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1765)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1765) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1766)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1766) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1767)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1767) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1960)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1961)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1962)] = (((((ry_outer_outer + (((((int)threadIdx.x) * 4) / 9) + 1)) < 8) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1518)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1963)] = (((((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1963) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 2) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 4) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 33) {
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 21) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((ff_outer_inner * 192) + (rc_outer_inner * 24))]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 119)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 22) {
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 52) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 2) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 58) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 110) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 6) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 116) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 70) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 8) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 122) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 76) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 10) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 82) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 134) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 14) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 140) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 50) {
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 94) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1197)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1198)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1199)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1206)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1207)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1208)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1215)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1216)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1217)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1224)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1225)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1226)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1242)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1243)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1244)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1251)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1252)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1253)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1260)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1261)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1262)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1269)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1270)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1271)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1278)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1279)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1280)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1287)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1288)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1289)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1296)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 145)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1297)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 146)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1298)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 153)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1305)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 154)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1306)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 155)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 162)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1314)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 163)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1315)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 164)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 171)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1323)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 172)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1324)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 173)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1325)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 180)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1332)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 181)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1333)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 182)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1334)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 189)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1341)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 190)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1342)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 191)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1343)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1350)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 199)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1351)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1352)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 207)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1359)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 208)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1360)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 209)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1361)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 216)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1368)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 217)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1369)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 218)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1370)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 225)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1377)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 226)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1378)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 227)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1379)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 234)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1386)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 235)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1387)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 236)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1388)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 243)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1395)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 244)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1396)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 245)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1397)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 252)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1404)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 253)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1405)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 254)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1406)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 261)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1413)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 262)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1414)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 263)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1415)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 270)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1422)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 271)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1423)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 272)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1424)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 279)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1431)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 280)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1432)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 281)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1433)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 288)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1440)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 289)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1441)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 290)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1442)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 297)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1449)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 298)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1450)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 299)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1451)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 306)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1458)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 307)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1459)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 308)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1460)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 315)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1467)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 316)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1468)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 317)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1469)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 324)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1476)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 325)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1477)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 326)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1478)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 333)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1485)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 334)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1486)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 335)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1487)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 342)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1494)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 343)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1495)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 344)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1496)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 351)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1503)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 352)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1504)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 353)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1505)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1512)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 361)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1513)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 362)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1514)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 369)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1521)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 370)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1522)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 371)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1523)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 378)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1530)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 379)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1531)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 380)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1532)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1539)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 388)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1540)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 389)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1541)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 396)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1548)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 397)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1549)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 398)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1550)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 405)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1557)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 406)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1558)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 407)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1559)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 414)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1566)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 415)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1567)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 416)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1568)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 423)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1575)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 424)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1576)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 425)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 433)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 434)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 441)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 442)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 443)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 450)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 451)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 452)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 459)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 460)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 461)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1613)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 468)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1620)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 469)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1621)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 470)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1622)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 477)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1629)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 478)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1630)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 479)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1631)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 486)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1638)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 487)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1639)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 488)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1640)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 495)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1647)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 496)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1648)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 497)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1649)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 504)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1656)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 505)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1657)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 506)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1658)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 513)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1665)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 514)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1666)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 515)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1667)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 522)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1674)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 523)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1675)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 524)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1676)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 531)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1683)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 532)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1684)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 533)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1685)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 540)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1692)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 541)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1693)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 542)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1694)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 549)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1701)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 550)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1702)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 551)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1703)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 558)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1710)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 559)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1711)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 560)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1712)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 567)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1719)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 568)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1720)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 569)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1721)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
}
}
@@ -808,7 +1411,7 @@ 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 41.682 seconds)
+ **Total running time of the script:** ( 2 minutes 36.362 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 4432ab7bb..50a974d90 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
@@ -646,7 +646,7 @@ 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)
- 10.1698 10.2085 10.2262 10.0747 0.0677
+ 9.7312 9.7496 9.7531 9.6909 0.0285
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 fcc11178e..0119ff881 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
@@ -665,7 +665,7 @@ 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)
- 755.8342 756.1985 756.3605 754.9437 0.6332
+ 765.8382 765.6893 767.0312 764.7941 0.9193
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.011 seconds)
+ **Total running time of the script:** ( 1 minutes 22.625 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 a56de9111..122ea968f 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
@@ -396,75 +396,78 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [256], [])[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_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 2) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16))
{
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ 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_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 2) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i0.outer*1024) + (i.outer.inner*512)) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ for (i0.inner: int32, 0, 4) {
+ let cse_var_22: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*32))
compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -521,7 +524,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.908 ms
+ Execution time of this operator: 3.114 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 50c13ab5c..a53dab567 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:43.107** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.568** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.077 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.535 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.016 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.020 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 933655879..10baab209 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
@@ -879,8 +879,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 42.35/42.35 result: MeasureResult(costs=(0.005466817526315789,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6181449890136719, timestamp=1655604934.3202896) [('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: 0.00/42.35 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.38/42.38 result: MeasureResult(costs=(0.005462087578947368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6693322658538818, timestamp=1655733478.5661983) [('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: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,7 +1003,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,7 +1126,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,7 +1249,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.38 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
@@ -1267,7 +1267,7 @@ 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: 0.00/42.35 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1390,7 +1390,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1513,7 +1513,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1636,7 +1636,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1759,7 +1759,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1882,7 +1882,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2005,7 +2005,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2128,7 +2128,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2251,7 +2251,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9bd2753fa2
+ 12: 0x00007f3492fe4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ 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: 141.88/141.88 result: MeasureResult(costs=(0.0016316605967741937,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1448559761047363, timestamp=1655604960.5619738) [('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: 144.84/144.84 result: MeasureResult(costs=(0.00159836847,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4229810237884521, timestamp=1655733505.158254) [('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
@@ -2461,7 +2461,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
- Time cost of this operator: 0.002077
+ Time cost of this operator: 0.002027
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 1f878b772..dea64c528 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
@@ -328,10 +328,10 @@ 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 318.5 98.767 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.954 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.279 (1, 1, 10, 10, 3) 1 1
- Total_time - 322.477 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.3 98.75 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.103 0.963 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.287 (1, 1, 10, 10, 3) 1 1
+ Total_time - 322.328 - - - -
@@ -397,10 +397,10 @@ 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 302.6 99.037 (1, 3, 10, 10, 2) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.1 0.687 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.276 (1, 3, 10, 10, 1) 1 1
- Total_time - 305.542 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 327.3 98.809 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.144 0.949 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.801 0.242 (1, 3, 10, 10, 1) 1 1
+ Total_time - 331.245 - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index ae6ed594c..971295b78 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -224,7 +224,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpekj1pstw/images/random'
+ '/tmp/tmpzc_21d_e/images/random'
@@ -324,8 +324,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpekj1pstw/images/target contains 8144 images
- /tmp/tmpekj1pstw/images/random contains 5000 images
+ /tmp/tmpzc_21d_e/images/target contains 8144 images
+ /tmp/tmpzc_21d_e/images/random contains 5000 images
@@ -500,13 +500,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2106 - accuracy: 0.9272 - val_loss: 0.1392 - val_accuracy: 0.9581
+ 328/328 - 55s - loss: 0.2191 - accuracy: 0.9258 - val_loss: 0.1354 - val_accuracy: 0.9592
Epoch 2/3
- 328/328 - 52s - loss: 0.0929 - accuracy: 0.9648 - val_loss: 0.1194 - val_accuracy: 0.9558
+ 328/328 - 52s - loss: 0.0967 - accuracy: 0.9633 - val_loss: 0.1141 - val_accuracy: 0.9664
Epoch 3/3
- 328/328 - 52s - loss: 0.0631 - accuracy: 0.9753 - val_loss: 0.1586 - val_accuracy: 0.9520
+ 328/328 - 52s - loss: 0.0652 - accuracy: 0.9763 - val_loss: 0.1310 - val_accuracy: 0.9585
- <keras.callbacks.History object at 0x7f7f81a17d50>
+ <keras.callbacks.History object at 0x7f2c606b3c10>
@@ -863,7 +863,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 13.555 seconds)
+ **Total running time of the script:** ( 4 minutes 12.914 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 979f64758..37f531d72 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**04:59.917** total execution time for **how_to_work_with_microtvm** files:
+**05:01.333** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:13.555 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:12.914 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.872 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:44.863 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.490 | 0.0 MB |
-+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.556 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``) | 00:00.000 | 0.0 MB |
++---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index bc8b79fbf..48e98b0fb 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.804** total execution time for **how_to_work_with_relay** files:
+**00:11.463** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.091 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.943 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.708 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.514 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index cd7cb8e94..39d06afaf 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f7f092649e0>
+ <function my_cuda_math_rule at 0x7f2bd12f2830>
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 0a30851c0..0d18e23bf 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
@@ -5,20 +5,20 @@
Computation times
=================
-**00:04.063** total execution time for **how_to_work_with_schedules** files:
+**00:04.249** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.884 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.973 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.974 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.003 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.518 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.559 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.513 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.540 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.102 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.033 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index fe45fa210..ee5520d70 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ 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/tmp4wfezi25/input0.cc'\nsource_filename = \"/tmp/tmp4wfezi25/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/tmpf_mjh9qi/input0.cc'\nsource_filename = \"/tmp/tmpf_mjh9qi/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 fd675f014..ce90bb2ba 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:21.158** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.531** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.151 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.524 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 975504d8f..4f750a6d3 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.98s!
+ resnet18_v1 inference graph built in 23.80s!
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 d38ff2c60..ed7ccfb9f 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.94s!
+ yolov3-tiny inference graph built in 16.41s!
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 b72620d64..5eb965c52 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:31.167** total execution time for **topic_vta_tutorials_frontend** files:
+**01:32.878** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.988 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.763 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.179 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:44.115 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index c038dd264..b958c35cd 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.155** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.275** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.773 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.858 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.382 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.417 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index bec8b3513..e027881be 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.670** total execution time for **topic_vta_tutorials** files:
+**00:00.765** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.344 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.398 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.326 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.367 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 2e03ae7d0..15aa87a1b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -334,7 +334,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.251 ms
+ Execution time of this operator: 93.791 ms
@@ -450,6 +450,11 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 6.970 seconds)
+
+
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 5cebf8f01..e8cb0188a 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.57/10.57 result: MeasureResult(costs=(0.025385777399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5395407676696777, timestamp=1655603786.3160706) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.94/10.57 result: MeasureResult(costs=(0.09143734220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6145367622375488, timestamp=1655603787.9458416) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.75/11.75 result: MeasureResult(costs=(0.0228490836,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5479917526245117, timestamp=1655603788.979352) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.85/11.75 result: MeasureResult(costs=(0.14544340039999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4420828819274902, timestamp=1655603791.4701326) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.63/11.75 result: MeasureResult(costs=(0.0739892636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3167030811309814, timestamp=1655603792.9196887) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.71/11.75 result: MeasureResult(costs=(0.15672989939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6239707469940186, timestamp=1655603796.0935812) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.87/11.75 result: MeasureResult(costs=(0.3098984232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.078963041305542, timestamp=1655603801.717946) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.43/11.75 result: MeasureResult(costs=(0.025726249200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5549643039703369, timestamp=1655603802.293098) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.90/11.75 result: MeasureResult(costs=(0.1411097294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3798537254333496, timestamp=1655603804.7938366) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.78/11.75 result: MeasureResult(costs=(0.09673240520000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6713755130767822, timestamp=1655603806.5056226) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 9.01/9.01 result: MeasureResult(costs=(0.029779154000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6099598407745361, timestamp=1655732313.546892) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.49/9.01 result: MeasureResult(costs=(0.10785634460000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8482446670532227, timestamp=1655732315.4355016) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.022798908599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5790083408355713, timestamp=1655732316.4734576) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.66/11.77 result: MeasureResult(costs=(0.1618017972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7039570808410645, timestamp=1655732319.7315443) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.57/11.77 result: MeasureResult(costs=(0.07527840820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3339087963104248, timestamp=1655732321.1948173) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.82/11.77 result: MeasureResult(costs=(0.1474598624,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.478830575942993, timestamp=1655732324.2326336) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.84/11.77 result: MeasureResult(costs=(0.3209505134,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.256069898605347, timestamp=1655732329.534552) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.24/11.77 result: MeasureResult(costs=(0.0262151928,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562058687210083, timestamp=1655732330.1164155) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.64/11.77 result: MeasureResult(costs=(0.1631957674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7320749759674072, timestamp=1655732332.969159) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.47/11.77 result: MeasureResult(costs=(0.10880448839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8636035919189453, timestamp=1655732334.873018) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 5aa715b70..a6c9a6944 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
.. code-block:: none
- {'mean': 497.4624736399983, 'median': 497.29978324999706, 'std': 1.4899553090543256}
+ {'mean': 500.9948443700159, 'median': 501.13534275001257, 'std': 0.7143444638204062}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 6.15 s
[Task 1/25] Current/Best: 6.17/ 17.34 GFLOPS | Progress: (8/20) | 9.00 s
[Task 1/25] Current/Best: 11.34/ 22.82 GFLOPS | Progress: (12/20) | 11.43 s
[Task 1/25] Current/Best: 16.72/ 22.83 GFLOPS | Progress: (16/20) | 13.10 s
[Task 1/25] Current/Best: 11.61/ 23.94 GFLOPS | Progress: (20/20) | 14.83 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.22/ 12.83 GFLOPS | Progress: (4/20) | 3.76 s
[Task 2/25] Current/Best: 13.99/ 17.67 GFLOPS | Progress: (8/20) | 5.04 s
[Task 2/25] Current/Best: 21.12/ 21.12 GFLOPS | Progress: (12/20) | 6.39 s
[Task 2/25] Current/Best: 12.85/ 21.12 GFLOPS | Progress: (16/20) | 7.67 s
[Task 2/25] Current/Best: 10.10/ 21.12 GFLOPS | Progress: (20/20) | 9.47 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.83 s
[Task 3/25] Current/Best: 15.53/ 16.84 GFLOPS | Progress: (8/20) | 7.77 s
[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.47 s
[Task 3/25] Current/Best: 7.21/ 23.77 GFLOPS | Progress: (16/20) | 11.38 s
[Task 3/25] Current/Best: 12.59/ 23.77 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.28 GFLOPS | Progress: (4/20) | 2.34 s
[Task 4/25] Current/Best: 6.84/ 20.28 GFLOPS | Progress: (8/20) | 6.68 s
[Task 4/25] Current/Best: 21.75/ 21.75 GFLOPS | Progress: (12/20) | 11.24 s
[Task 4/25] Current/Best: 17.29/ 21.75 GFLOPS | Progress: (16/20) | 13.48 s
[Task 4/25] Current/Best: 13.10/ 21.75 GFLOPS | Progress: (20/20) | 15.51 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.37/ 10.21 GFLOPS | Progress: (4/20) | 2.58 s
[Task 5/25] Current/Best: 11.67/ 12.51 GFLOPS | Progress: (8/20) | 4.64 s
[Task 5/25] Current/Best: 10.73/ 18.07 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 11.50/ 22.64 GFLOPS | Progress: (16/20) | 9.16 s
[Task 5/25] Current/Best: 11.82/ 22.64 GFLOPS | Progress: (20/20) | 11.03 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.14/ 20.74 GFLOPS | Progress: (4/20) | 3.97 s
[Task 6/25] Current/Best: 18.96/ 20.74 GFLOPS | Progress: (8/20) | 5.73 s
[Task 6/25] Current/Best: 13.33/ 20.74 GFLOPS | Progress: (12/20) | 7.66 s
[Task 6/25] Current/Best: 19.97/ 20.74 GFLOPS | Progress: (16/20) | 9.88 s
[Task 6/25] Current/Best: 3.73/ 20.74 GFLOPS | Progress: (20/20) | 12.42 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.17/ 12.90 GFLOPS | Progress: (4/20) | 3.51 s
[Task 7/25] Current/Best: 20.19/ 21.05 GFLOPS | Progress: (8/20) | 5.02 s
[Task 7/25] Current/Best: 15.85/ 21.05 GFLOPS | Progress: (12/20) | 6.94 s
[Task 7/25] Current/Best: 12.23/ 21.05 GFLOPS | Progress: (16/20) | 9.00 s
[Task 7/25] Current/Best: 6.31/ 21.05 GFLOPS | Progress: (20/20) | 11.48 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.90/ 13.85 GFLOPS | Progress: (4/20) | 2.86 s
[Task 8/25] Current/Best: 9.45/ 13.85 GFLOPS | Progress: (8/20) | 7.74 s
[Task 8/25] Current/Best: 12.57/ 13.85 GFLOPS | Progress: (12/20) | 13.99 s
[Task 8/25] Current/Best: 18.89/ 18.89 GFLOPS | Progress: (16/20) | 16.07 s
[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 22.51 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.34/ 15.31 GFLOPS | Progress: (4/20) | 11.88 s
[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.67 s
[Task 9/25] Current/Best: 8.32/ 23.41 GFLOPS | Progress: (12/20) | 16.08 s
[Task 9/25] Current/Best: 17.84/ 23.41 GFLOPS | Progress: (16/20) | 18.68 s
[Task 9/25] Current/Best: 9.00/ 23.41 GFLOPS | Progress: (20/20) | 26.32 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (4/20) | 2.55 s
[Task 10/25] Current/Best: 15.52/ 18.28 GFLOPS | Progress: (8/20) | 4.13 s
[Task 10/25] Current/Best: 12.32/ 19.04 GFLOPS | Progress: (12/20) | 5.65 s
[Task 10/25] Current/Best: 19.09/ 20.61 GFLOPS | Progress: (16/20) | 6.76 s
[Task 10/25] Current/Best: 8.85/ 20.61 GFLOPS | Progress: (20/20
) | 8.29 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.28/ 18.09 GFLOPS | Progress: (4/20) | 3.27 s
[Task 11/25] Current/Best: 16.75/ 18.09 GFLOPS | Progress: (8/20) | 6.03 s
[Task 11/25] Current/Best: 16.12/ 18.09 GFLOPS | Progress: (12/20) | 8.10 s
[Task 11/25] Current/Best: 13.45/ 21.19 GFLOPS | Progress: (16/20) | 10.88 s
[Task 11/25] Current/Best: 19.33/ 21.19 GFLOPS | Progress: (20/20) | 12.92 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 18.09 GFLOPS | Progress: (4/20) | 5.40 s
[Task 12/25] Current/Best: 5.21/ 18.09 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 11.10 s
[Task 12/25] Current/Best: 13.55/ 19.28 GFLOPS | Progress: (16/20) | 13.90 s
[Task 12/25] Current/Best: 15.12/ 19.28 GFLOPS | Progress: (20/20) | 15.86 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.78/ 17.20 GFLOPS | Progress: (4/20) | 3.63 s
[Task 13/25] Current/Best: 16.03/ 20.88 GFLOPS | Progress: (8/20) | 6.06 s
[Task 13/25] Current/Best: 19.45/ 21.63 GFLOPS | Progress: (12/20) | 8.95 s
[Task 13/25] Current/Best: 12.22/ 21.63 GFLOPS | Progress: (16/20) | 12.37 s
[Task 13/25] Current/Best: 18.80/ 21.63 GFLOPS | Progress: (20/20) | 14.64 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.30 s
[Task 14/25] Current/Best: 6.09/ 13.57 GFLOPS | Progress: (8/20) | 5.45 s
[Task 14/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (12/20) | 7.98 s
[Task 14/25] Current/Best: 16.90/ 20.64 GFLOPS | Progress: (16/20) | 9.62 s Done.
-
[Task 14/25] Current/Best: 17.21/ 20.64 GFLOPS | Progress: (20/20) | 11.36 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.09/ 17.57 GFLOPS | Progress: (4/20) | 2.68 s
[Task 15/25] Current/Best: 14.26/ 17.99 GFLOPS | Progress: (8/20) | 4.02 s
[Task 15/25] Current/Best: 10.38/ 22.18 GFLOPS | Progress: (12/20) | 6.15 s
[Task 15/25] Current/Best: 20.28/ 22.18 GFLOPS | Progress: (16/20) | 9.20 s
[Task 15/25] Current/Best: 9.68/ 22.18 GFLOPS | Progress: (20/20) | 10.23 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (4/20) | 2.97 s
[Task 16/25] Current/Best: 3.02/ 19.57 GFLOPS | Progress: (8/20) | 4.59 s
[Task 16/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (12/20) | 5.80 s
[Task 16/25] Current/Best: 17.50/ 19.58 GFLOPS | Progress: (16/20) |
7.16 s
[Task 16/25] Current/Best: 9.95/ 22.22 GFLOPS | Progress: (20/20) | 9.21 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.16/ 18.81 GFLOPS | Progress: (4/20) | 4.66 s
[Task 17/25] Current/Best: 14.36/ 23.01 GFLOPS | Progress: (8/20) | 7.53 s
[Task 17/25] Current/Best: 16.76/ 23.01 GFLOPS | Progress: (12/20) | 9.60 s
[Task 17/25] Current/Best: 17.13/ 23.01 GFLOPS | Progress: (16/20) | 11.74 s
[Task 17/25] Current/Best: 10.02/ 23.01 GFLOPS | Progress: (20/20) | 13.86 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.10/ 17.83 GFLOPS | Progress: (4/20) | 3.67 s
[Task 18/25] Current/Best: 10.53/ 19.89 GFLOPS | Progress: (8/20) | 7.13 s
[Task 18/25] Current/Best: 19.03/ 19.89 GFLOPS | Progress: (12/20) | 9.05 s
[Task 18/25] Current/Best: 9.91/ 19.89 GFLOPS | Progress: (16/20) | 12.62 s
[Task 18/25] Current/Best: 20.23/ 20.23 GFLOPS | Progress: (20/20) | 14.15 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.04/ 20.22 GFLOPS | Progress: (4/20) | 6.06 s
[Task 19/25] Current/Best: 2.59/ 20.22 GFLOPS | Progress: (8/20) | 9.32 s
[Task 19/25] Current/Best: 19.50/ 20.72 GFLOPS | Progress: (12/20) | 12.19 s
[Task 19/25] Current/Best: 14.01/ 21.36 GFLOPS | Progress: (16/20) | 15.05 s
[Task 19/25] Current/Best: 2.70/ 23.29 GFLOPS | Progress: (20/20) | 17.81 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.71/ 15.08 GFLOPS | Progress: (4/20) | 3.31 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.40/ 17.40 GFLOPS | Progress: (4/20) | 6.29 s
[Task 1/25] Current/Best: 6.16/ 17.40 GFLOPS | Progress: (8/20) | 9.21 s
[Task 1/25] Current/Best: 11.53/ 22.67 GFLOPS | Progress: (12/20) | 11.67 s
[Task 1/25] Current/Best: 16.69/ 22.67 GFLOPS | Progress: (16/20) | 13.37 s
[Task 1/25] Current/Best: 11.59/ 23.79 GFLOPS | Progress: (20/20) | 15.12 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.21/ 12.81 GFLOPS | Progress: (4/20) | 3.81 s
[Task 2/25] Current/Best: 14.14/ 18.28 GFLOPS | Progress: (8/20) | 5.13 s
[Task 2/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (12/20) | 6.47 s
[Task 2/25] Current/Best: 13.16/ 21.19 GFLOPS | Progress: (16/20) | 7.75 s
[Task 2/25] Current/Best: 19.80/ 21.19 GFLOPS | Progress: (20/20) | 9.34 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.50 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.52/ 16.86 GFLOPS | Progress: (8/20) | 7.79 s
[Task 3/25] Current/Best: 14.80/ 16.86 GFLOPS | Progress: (12/20) | 9.52 s
[Task 3/25] Current/Best: 7.18/ 23.76 GFLOPS | Progress: (16/20) | 11.44 s
[Task 3/25] Current/Best: 12.48/ 23.76 GFLOPS | Progress: (20/20) | 15.97 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.35 GFLOPS | Progress: (4/20) | 2.40 s
[Task 4/25] Current/Best: 6.44/ 20.35 GFLOPS | Progress: (8/20) | 6.74 s
[Task 4/25] Current/Best: 21.80/ 21.80 GFLOPS | Progress: (12/20) | 11.17 s
[Task 4/25] Current/Best: 17.02/ 21.80 GFLOPS | Progress: (16/20) | 13.38 s
[Task 4/25] Current/Best: 13.44/ 21.80 GFLOPS | Progress: (20/20) | 15.28 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.83/ 10.34 GFLOPS | Progress: (4/20) | 2.57 s
[Task 5/25] Current/Best: 11.75/ 12.91 GFLOPS | Progress: (8/20) | 4.61 s
[Task 5/25] Current/Best: 11.08/ 17.78 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 12.00/ 22.48 GFLOPS | Progress: (16/20) | 9.14 s
[Task 5/25] Current/Best: 12.04/ 22.48 GFLOPS | Progress: (20/20) | 10.99 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.13/ 20.82 GFLOPS | Progress: (4/20) | 3.95 s
[Task 6/25] Current/Best: 19.01/ 20.82 GFLOPS | Progress: (8/20) | 5.71 s
[Task 6/25] Current/Best: 12.99/ 20.82 GFLOPS | Progress: (12/20) | 7.63 s
[Task 6/25] Current/Best: 19.82/ 20.82 GFLOPS | Progress: (16/20) | 9.87 s
[Task 6/25] Current/Best: 3.76/ 20.82 GFLOPS | Progress: (20/20) | 12.40 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.16/ 12.82 GFLOPS | Progress: (4/20) | 3.63 s
[Task 7/25] Current/Best: 20.35/ 21.18 GFLOPS | Progress: (8/20) | 5.15 s
[Task 7/25] Current/Best: 15.98/ 21.18 GFLOPS | Progress: (12/20) | 7.10 s
[Task 7/25] Current/Best: 12.26/ 21.18 GFLOPS | Progress: (16/20) | 9.15 s
[Task 7/25] Current/Best: 6.41/ 21.74 GFLOPS | Progress: (20/20) | 11.62 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.50/ 14.53 GFLOPS | Progress: (4/20) | 2.88 s
[Task 8/25] Current/Best: 9.81/ 14.53 GFLOPS | Progress: (8/20) | 7.67 s
[Task 8/25] Current/Best: 13.36/ 14.53 GFLOPS | Progress: (12/20) | 13.77 s
[Task 8/25] Current/Best: 18.98/ 18.98 GFLOPS | Progress: (16/20) | 15.87 s
[Task 8/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (20/20) | 22.41 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.24/ 15.66 GFLOPS | Progress: (4/20) | 11.96 s
[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.71 s
[Task 9/25] Current/Best: 8.25/ 23.41 GFLOPS | Progress: (12/20) | 16.11 s
[Task 9/25] Current/Best: 17.97/ 23.41 GFLOPS | Progress: (16/20) | 18.78 s
[Task 9/25] Current/Best: 8.89/ 23.41 GFLOPS | Progress: (20/20) | 26.57 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.57/ 18.57 GFLOPS | Progress: (4/20) | 2.56 s
[Task 10/25] Current/Best: 15.61/ 18.57 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 12.80/ 19.00 GFLOPS | Progress: (12/20) | 5.67 s
[Task 10/25] Current/Best: 19.15/ 20.32 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.91/ 20.32 GFLOPS | Progress: (20/20
) | 8.35 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.24/ 18.06 GFLOPS | Progress: (4/20) | 3.35 s
[Task 11/25] Current/Best: 15.14/ 18.06 GFLOPS | Progress: (8/20) | 6.14 s
[Task 11/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (12/20) | 8.16 s
[Task 11/25] Current/Best: 13.42/ 21.09 GFLOPS | Progress: (16/20) | 10.95 s
[Task 11/25] Current/Best: 19.41/ 21.58 GFLOPS | Progress: (20/20) | 12.98 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.71/ 18.23 GFLOPS | Progress: (4/20) | 5.34 s
[Task 12/25] Current/Best: 5.30/ 18.23 GFLOPS | Progress: (8/20) | 9.05 s
[Task 12/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (12/20) | 11.03 s
[Task 12/25] Current/Best: 14.38/ 18.93 GFLOPS | Progress: (16/20) | 13.82 s
[Task 12/25] Current/Best: 15.08/ 19.26 GFLOPS | Progress: (20/20) | 15.74 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.02/ 17.38 GFLOPS | Progress: (4/20) | 3.64 s
[Task 13/25] Current/Best: 16.04/ 20.88 GFLOPS | Progress: (8/20) | 6.07 s
[Task 13/25] Current/Best: 19.44/ 21.51 GFLOPS | Progress: (12/20) | 8.94 s
[Task 13/25] Current/Best: 12.23/ 21.51 GFLOPS | Progress: (16/20) | 12.37 s
[Task 13/25] Current/Best: 18.54/ 21.51 GFLOPS | Progress: (20/20) | 14.61 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.51/ 13.51 GFLOPS | Progress: (4/20) | 3.31 s
[Task 14/25] Current/Best: 6.12/ 13.51 GFLOPS | Progress: (8/20) | 5.50 s
[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 8.04 s
[Task 14/25] Current/Best: 16.66/ 20.49 GFLOPS | Progress: (16/20) | 9.70 s Done.
+
[Task 14/25] Current/Best: 17.30/ 20.49 GFLOPS | Progress: (20/20) | 11.42 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.20/ 17.57 GFLOPS | Progress: (4/20) | 2.65 s
[Task 15/25] Current/Best: 14.36/ 18.00 GFLOPS | Progress: (8/20) | 3.95 s
[Task 15/25] Current/Best: 10.38/ 22.29 GFLOPS | Progress: (12/20) | 5.99 s
[Task 15/25] Current/Best: 20.23/ 22.29 GFLOPS | Progress: (16/20) | 8.93 s
[Task 15/25] Current/Best: 9.59/ 22.29 GFLOPS | Progress: (20/20) | 9.95 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (4/20) | 2.95 s
[Task 16/25] Current/Best: 3.04/ 20.35 GFLOPS | Progress: (8/20) | 4.58 s
[Task 16/25] Current/Best: 19.08/ 20.35 GFLOPS | Progress: (12/20) | 5.80 s
[Task 16/25] Current/Best: 17.78/ 20.35 GFLOPS | Progress: (16/20) |
7.15 s
[Task 16/25] Current/Best: 10.08/ 22.00 GFLOPS | Progress: (20/20) | 9.21 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.62/ 18.89 GFLOPS | Progress: (4/20) | 4.70 s
[Task 17/25] Current/Best: 14.51/ 23.16 GFLOPS | Progress: (8/20) | 7.58 s
[Task 17/25] Current/Best: 16.80/ 23.16 GFLOPS | Progress: (12/20) | 9.61 s
[Task 17/25] Current/Best: 16.54/ 23.16 GFLOPS | Progress: (16/20) | 11.74 s
[Task 17/25] Current/Best: 9.75/ 23.16 GFLOPS | Progress: (20/20) | 13.89 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.59/ 17.71 GFLOPS | Progress: (4/20) | 3.69 s
[Task 18/25] Current/Best: 10.64/ 19.66 GFLOPS | Progress: (8/20) | 7.11 s
[Task 18/25] Current/Best: 19.30/ 19.66 GFLOPS | Progress: (12/20) | 9.03 s
[Task 18/25] Current/Best: 9.84/ 19.66 GFLOPS | Progress: (16/20) | 12.62 s
[Task 18/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (20/20) | 14.16 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.35/ 20.20 GFLOPS | Progress: (4/20) | 6.26 s
[Task 19/25] Current/Best: 2.60/ 20.20 GFLOPS | Progress: (8/20) | 9.54 s
[Task 19/25] Current/Best: 18.73/ 20.83 GFLOPS | Progress: (12/20) | 12.31 s
[Task 19/25] Current/Best: 15.33/ 21.48 GFLOPS | Progress: (16/20) | 15.13 s
[Task 19/25] Current/Best: 2.70/ 23.20 GFLOPS | Progress: (20/20) | 17.90 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.56/ 15.03 GFLOPS | Progress: (4/20) | 3.33 s Done.
Done.
-
[Task 20/25] Current/Best: 10.12/ 15.08 GFLOPS | Progress: (8/20) | 6.62 s
[Task 20/25] Current/Best: 2.33/ 16.68 GFLOPS | Progress: (12/20) | 10.68 s
[Task 20/25] Current/Best: 12.48/ 16.68 GFLOPS | Progress: (16/20) | 14.29 s
[Task 20/25] Current/Best: 13.09/ 21.77 GFLOPS | Progress: (20/20) | 16.37 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.47 GFLOPS | Progress: (4/20) | 3.19 s
[Task 21/25] Current/Best: 14.27/ 17.47 GFLOPS | Progress: (8/20) | 4.84 s
[Task 21/25] Current/Best: 1.61/ 17.47 GFLOPS | Progress: (12/20) | 7.00 s
[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (16/20) | 10.44 s
[Task 21/25] Current/Best: 4.46/ 18.14 GFLOPS | Progress: (20/20) | 17.66 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.04 GFLOPS | Progress: (4/20
) | 2.67 s
[Task 22/25] Current/Best: 8.73/ 21.02 GFLOPS | Progress: (8/20) | 4.64 s
[Task 22/25] Current/Best: 20.09/ 21.02 GFLOPS | Progress: (12/20) | 6.99 s
[Task 22/25] Current/Best: 14.83/ 21.02 GFLOPS | Progress: (16/20) | 9.06 s
[Task 22/25] Current/Best: 14.20/ 21.02 GFLOPS | Progress: (20/20) | 10.77 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.41/ 20.24 GFLOPS | Progress: (4/20) | 3.20 s
[Task 23/25] Current/Best: 14.47/ 20.24 GFLOPS | Progress: (8/20) | 6.54 s
[Task 23/25] Current/Best: 20.78/ 21.33 GFLOPS | Progress: (12/20) | 8.36 s
[Task 23/25] Current/Best: 6.34/ 21.33 GFLOPS | Progress: (16/20) | 15.46 s
[Task 23/25] Current/Best: 7.65/ 21.33 GFLOPS | Progress: (20/20) | 19.67 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.78 s
[Task 24/25] Current/Best: 1.96/ 8.40 GFLOPS | Progress: (8/20) | 22.81 s
[Task 24/25] Current/Best: 4.47/ 8.40 GFLOPS | Progress: (12/20) | 34.35 s Done.
+
[Task 20/25] Current/Best: 10.36/ 15.03 GFLOPS | Progress: (8/20) | 6.76 s
[Task 20/25] Current/Best: 2.32/ 16.59 GFLOPS | Progress: (12/20) | 10.67 s
[Task 20/25] Current/Best: 12.60/ 16.59 GFLOPS | Progress: (16/20) | 14.47 s
[Task 20/25] Current/Best: 13.45/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.56 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.52/ 17.56 GFLOPS | Progress: (8/20) | 4.77 s
[Task 21/25] Current/Best: 1.61/ 17.56 GFLOPS | Progress: (12/20) | 6.86 s
[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 10.32 s
[Task 21/25] Current/Best: 4.45/ 18.28 GFLOPS | Progress: (20/20) | 17.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20
) | 2.68 s
[Task 22/25] Current/Best: 9.20/ 21.49 GFLOPS | Progress: (8/20) | 4.58 s
[Task 22/25] Current/Best: 19.91/ 21.49 GFLOPS | Progress: (12/20) | 6.93 s
[Task 22/25] Current/Best: 15.19/ 21.49 GFLOPS | Progress: (16/20) | 9.00 s
[Task 22/25] Current/Best: 15.13/ 21.49 GFLOPS | Progress: (20/20) | 10.67 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.37/ 20.18 GFLOPS | Progress: (4/20) | 3.23 s
[Task 23/25] Current/Best: 15.80/ 20.18 GFLOPS | Progress: (8/20) | 6.60 s
[Task 23/25] Current/Best: 20.85/ 21.25 GFLOPS | Progress: (12/20) | 8.42 s
[Task 23/25] Current/Best: 6.45/ 21.25 GFLOPS | Progress: (16/20) | 15.48 s
[Task 23/25] Current/Best: 7.67/ 21.25 GFLOPS | Progress: (20/20) | 19.70 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.50/ 8.50 GFLOPS | Progress: (4/20) | 11.73 s
[Task 24/25] Current/Best: 1.97/ 8.50 GFLOPS | Progress: (8/20) | 22.76 s
[Task 24/25] Current/Best: 4.61/ 8.50 GFLOPS | Progress: (12/20) | 34.29 s Done.
Done.
-
[Task 24/25] Current/Best: 7.05/ 8.92 GFLOPS | Progress: (16/20) | 39.93 s
[Task 24/25] Current/Best: 3.37/ 8.92 GFLOPS | Progress: (20/20) | 45.89 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.54/ 2.90 GFLOPS | Progress: (4/20) | 11.57 s
[Task 25/25] Current/Best: 5.67/ 7.70 GFLOPS | Progress: (8/20) | 22.78 s
[Task 25/25] Current/Best: 6.05/ 7.70 GFLOPS | Progress: (12/20) | 34.18 s
[Task 25/25] Current/Best: 5.82/ 9.20 GFLOPS | Progress: (16/20) | 35.89 s
[Task 25/25] Current/Best: 2.92/ 9.20 GFLOPS | Progress: (20/20) | 46.58 s
+
[Task 24/25] Current/Best: 7.17/ 8.85 GFLOPS | Progress: (16/20) | 39.79 s
[Task 24/25] Current/Best: 3.24/ 8.88 GFLOPS | Progress: (20/20) | 45.68 s Done.
+
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.55/ 2.92 GFLOPS | Progress: (4/20) | 11.59 s
[Task 25/25] Current/Best: 5.87/ 8.01 GFLOPS | Progress: (8/20) | 22.83 s
[Task 25/25] Current/Best: 5.93/ 8.01 GFLOPS | Progress: (12/20) | 34.24 s
[Task 25/25] Current/Best: 5.86/ 9.48 GFLOPS | Progress: (16/20) | 35.98 s
[Task 25/25] Current/Best: 2.89/ 9.48 GFLOPS | Progress: (20/20) | 46.69 s
@@ -677,7 +677,7 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 417.4679863499978, 'median': 418.44872064999663, 'std': 2.3841485033104615}
- unoptimized: {'mean': 497.4624736399983, 'median': 497.29978324999706, 'std': 1.4899553090543256}
+ optimized: {'mean': 414.44940566000696, 'median': 414.5539063999877, 'std': 0.6336221096039909}
+ unoptimized: {'mean': 500.9948443700159, 'median': 501.13534275001257, 'std': 0.7143444638204062}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 17.706 seconds)
+ **Total running time of the script:** ( 10 minutes 18.620 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 66e687fb9..e2d61b493 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.298e-07 secs/op
+ 1.266e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 3f21df971..bab83034e 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0xcf5c200)), stage(b, placeholder(b, 0x232fd140)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x20b649f0)), stage(b, placeholder(b, 0x1a63ed80)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index ad306e288..9929c80cf 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**13:10.433** total execution time for **tutorial** files:
+**13:20.293** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:17.706 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:18.620 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:00.476 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:06.970 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:58.211 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.989 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.416 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.353 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.544 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.756 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:01.253 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.757 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.675 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.151 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.172 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index b97dba22e..8e2088c22 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -288,8 +288,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000009
- naive: 0.000006
+ Numpy running time: 0.000008
+ naive: 0.000008
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.542999999008317e-06 1.0
- naive 5.9193e-06 0.692883062236582
- parallel 6.9181e-06 0.8097974951191692
- vector 2.4738799999999998e-05 2.8957977294711124
+ numpy 7.755080005154014e-06 1.0
+ naive 8.0261e-06 1.0349474144258817
+ parallel 6.9596e-06 0.8974246552420685
+ vector 2.47975e-05 3.1975814541590313
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019346
+ Numpy running time: 0.019455
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.350288
+ none: 3.313207
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.307988
+ blocking: 0.316026
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.349094
+ vectorization: 0.346220
@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], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.119802
+ loop permutation: 0.119249
@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], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.110999
+ array packing: 0.110582
@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], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.111005
+ block caching: 0.111336
@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], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.145153
+ parallelization: 0.144375
@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], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.3502878743 1.0
- blocking 0.3079883106 0.09192890944165513
- vectorization 0.3490941228 0.10419824680675799
- loop permutation 0.1198024985 0.03575886699737144
- array packing 0.1109986171 0.03313106851249066
- block caching 0.11100475349999998 0.03313290011629016
- parallelization 0.14515298299999999 0.04332552558049294
+ none 3.3132068332 1.0
+ blocking 0.3160257106 0.09538363480156545
+ vectorization 0.3462197748 0.10449687937701431
+ loop permutation 0.11924868389999999 0.03599192260050539
+ array packing 0.1105820952 0.0333761520989006
+ block caching 0.11133638770000001 0.0336038144628803
+ parallelization 0.1443750433 0.043575620408991496
@@ -1673,11 +1673,6 @@ 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 0.476 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 938b65fd8..48ab3a17f 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-9bba7580b0dcaea4963bd6b35df0bf6bf867b8ff
+8bf6cd5800daaf42935fd69cbd63180c97bef262
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 9328e4efd..4fae14dd0 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -403,7 +403,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip1aefc1d6-d6a9-424f-87e5-0b0fcb892af8 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipe51c9289-499f-45fe-8168-5039d762f3c4 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 07ba5c704..898d1f91a 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -408,46 +408,95 @@ 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<05:17, 137kB/s]
- 0%| | 96.0k/41.5M [00:00<03:46, 192kB/s]
- 0%| | 160k/41.5M [00:00<02:52, 252kB/s]
- 1%| | 304k/41.5M [00:00<01:38, 440kB/s]
- 1%|1 | 608k/41.5M [00:01<00:50, 845kB/s]
- 3%|2 | 1.19M/41.5M [00:01<00:25, 1.64MB/s]
- 6%|5 | 2.30M/41.5M [00:01<00:13, 3.04MB/s]
- 8%|7 | 3.29M/41.5M [00:01<00:10, 3.64MB/s]
- 11%|#1 | 4.76M/41.5M [00:01<00:07, 4.97MB/s]
- 15%|#5 | 6.23M/41.5M [00:02<00:06, 5.91MB/s]
- 19%|#8 | 7.68M/41.5M [00:02<00:05, 6.52MB/s]
- 22%|##2 | 9.16M/41.5M [00:02<00:04, 7.00MB/s]
- 26%|##5 | 10.6M/41.5M [00:02<00:04, 7.32MB/s]
- 29%|##9 | 12.1M/41.5M [00:02<00:04, 7.55MB/s]
- 33%|###2 | 13.6M/41.5M [00:03<00:03, 7.70MB/s]
- 36%|###6 | 15.0M/41.5M [00:03<00:03, 7.81MB/s]
- 40%|###9 | 16.5M/41.5M [00:03<00:03, 7.89MB/s]
- 43%|####3 | 18.0M/41.5M [00:03<00:03, 7.90MB/s]
- 47%|####6 | 19.4M/41.5M [00:03<00:02, 8.90MB/s]
- 50%|##### | 20.9M/41.5M [00:03<00:02, 9.96MB/s]
- 53%|#####2 | 21.9M/41.5M [00:04<00:02, 8.83MB/s]
- 55%|#####4 | 22.8M/41.5M [00:04<00:02, 7.68MB/s]
- 57%|#####7 | 23.8M/41.5M [00:04<00:02, 7.08MB/s]
- 61%|###### | 25.3M/41.5M [00:04<00:02, 8.35MB/s]
- 64%|######4 | 26.8M/41.5M [00:04<00:01, 9.45MB/s]
- 67%|######6 | 27.7M/41.5M [00:04<00:01, 8.52MB/s]
- 69%|######8 | 28.6M/41.5M [00:04<00:01, 7.36MB/s]
- 72%|#######1 | 29.7M/41.5M [00:05<00:01, 7.96MB/s]
- 75%|#######5 | 31.2M/41.5M [00:05<00:01, 9.21MB/s]
- 77%|#######7 | 32.1M/41.5M [00:05<00:01, 8.25MB/s]
- 79%|#######9 | 32.9M/41.5M [00:05<00:01, 7.11MB/s]
- 82%|########2 | 34.1M/41.5M [00:05<00:01, 6.94MB/s]
- 86%|########5 | 35.6M/41.5M [00:05<00:00, 8.51MB/s]
- 89%|########8 | 36.8M/41.5M [00:05<00:00, 9.28MB/s]
- 91%|######### | 37.7M/41.5M [00:06<00:00, 7.92MB/s]
- 93%|#########2| 38.6M/41.5M [00:06<00:00, 6.93MB/s]
- 96%|#########6| 40.0M/41.5M [00:06<00:00, 8.64MB/s]
- 99%|#########8| 40.9M/41.5M [00:06<00:00, 8.79MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 6.49MB/s]
+ 0%| | 16.0k/41.5M [00:00<08:10, 88.6kB/s]
+ 0%| | 40.0k/41.5M [00:00<06:27, 112kB/s]
+ 0%| | 64.0k/41.5M [00:00<06:00, 120kB/s]
+ 0%| | 96.0k/41.5M [00:00<04:56, 146kB/s]
+ 0%| | 120k/41.5M [00:00<04:59, 145kB/s]
+ 0%| | 152k/41.5M [00:01<04:31, 160kB/s]
+ 0%| | 176k/41.5M [00:01<04:46, 151kB/s]
+ 0%| | 208k/41.5M [00:01<04:35, 157kB/s]
+ 1%| | 240k/41.5M [00:01<04:24, 164kB/s]
+ 1%| | 280k/41.5M [00:01<03:53, 185kB/s]
+ 1%| | 312k/41.5M [00:01<03:51, 187kB/s]
+ 1%| | 344k/41.5M [00:02<03:50, 187kB/s]
+ 1%| | 384k/41.5M [00:02<03:35, 200kB/s]
+ 1%| | 424k/41.5M [00:02<03:28, 206kB/s]
+ 1%|1 | 464k/41.5M [00:02<03:25, 210kB/s]
+ 1%|1 | 512k/41.5M [00:02<03:11, 224kB/s]
+ 1%|1 | 552k/41.5M [00:03<03:11, 225kB/s]
+ 1%|1 | 600k/41.5M [00:03<02:57, 242kB/s]
+ 2%|1 | 656k/41.5M [00:03<02:39, 268kB/s]
+ 2%|1 | 704k/41.5M [00:03<02:36, 273kB/s]
+ 2%|1 | 760k/41.5M [00:03<02:31, 282kB/s]
+ 2%|1 | 816k/41.5M [00:03<02:28, 287kB/s]
+ 2%|2 | 872k/41.5M [00:04<02:25, 293kB/s]
+ 2%|2 | 936k/41.5M [00:04<02:13, 318kB/s]
+ 2%|2 | 0.98M/41.5M [00:04<02:06, 336kB/s]
+ 3%|2 | 1.05M/41.5M [00:04<01:52, 376kB/s]
+ 3%|2 | 1.13M/41.5M [00:04<01:45, 400kB/s]
+ 3%|2 | 1.22M/41.5M [00:05<01:39, 424kB/s]
+ 3%|3 | 1.30M/41.5M [00:05<01:36, 438kB/s]
+ 3%|3 | 1.41M/41.5M [00:05<01:27, 482kB/s]
+ 4%|3 | 1.52M/41.5M [00:05<01:18, 534kB/s]
+ 4%|3 | 1.63M/41.5M [00:05<01:11, 585kB/s]
+ 4%|4 | 1.76M/41.5M [00:05<01:06, 631kB/s]
+ 5%|4 | 1.90M/41.5M [00:06<01:01, 680kB/s]
+ 5%|4 | 2.05M/41.5M [00:06<00:57, 725kB/s]
+ 5%|5 | 2.20M/41.5M [00:06<00:53, 774kB/s]
+ 6%|5 | 2.38M/41.5M [00:06<00:48, 851kB/s]
+ 6%|6 | 2.56M/41.5M [00:06<00:43, 933kB/s]
+ 7%|6 | 2.76M/41.5M [00:07<00:40, 994kB/s]
+ 7%|7 | 2.97M/41.5M [00:07<00:38, 1.06MB/s]
+ 8%|7 | 3.20M/41.5M [00:07<00:35, 1.12MB/s]
+ 8%|8 | 3.43M/41.5M [00:07<00:34, 1.17MB/s]
+ 9%|8 | 3.69M/41.5M [00:07<00:31, 1.26MB/s]
+ 10%|9 | 3.96M/41.5M [00:07<00:28, 1.38MB/s]
+ 10%|# | 4.26M/41.5M [00:08<00:26, 1.50MB/s]
+ 11%|#1 | 4.57M/41.5M [00:08<00:24, 1.61MB/s]
+ 12%|#1 | 4.90M/41.5M [00:08<00:22, 1.70MB/s]
+ 13%|#2 | 5.25M/41.5M [00:08<00:21, 1.79MB/s]
+ 14%|#3 | 5.61M/41.5M [00:08<00:20, 1.85MB/s]
+ 14%|#4 | 5.99M/41.5M [00:09<00:19, 1.93MB/s]
+ 15%|#5 | 6.41M/41.5M [00:09<00:17, 2.09MB/s]
+ 17%|#6 | 6.85M/41.5M [00:09<00:16, 2.27MB/s]
+ 18%|#7 | 7.31M/41.5M [00:09<00:14, 2.42MB/s]
+ 19%|#8 | 7.80M/41.5M [00:09<00:13, 2.55MB/s]
+ 20%|## | 8.32M/41.5M [00:09<00:13, 2.66MB/s]
+ 21%|##1 | 8.86M/41.5M [00:10<00:12, 2.71MB/s]
+ 23%|##2 | 9.44M/41.5M [00:10<00:10, 3.20MB/s]
+ 24%|##4 | 10.1M/41.5M [00:10<00:08, 3.69MB/s]
+ 25%|##5 | 10.4M/41.5M [00:10<00:08, 3.66MB/s]
+ 26%|##6 | 10.8M/41.5M [00:10<00:10, 3.18MB/s]
+ 27%|##7 | 11.4M/41.5M [00:10<00:08, 3.76MB/s]
+ 29%|##9 | 12.1M/41.5M [00:10<00:07, 3.94MB/s]
+ 31%|### | 12.9M/41.5M [00:11<00:06, 4.81MB/s]
+ 32%|###2 | 13.4M/41.5M [00:11<00:06, 4.23MB/s]
+ 33%|###3 | 13.8M/41.5M [00:11<00:08, 3.61MB/s]
+ 35%|###4 | 14.5M/41.5M [00:11<00:06, 4.34MB/s]
+ 37%|###7 | 15.4M/41.5M [00:11<00:05, 4.64MB/s]
+ 39%|###9 | 16.3M/41.5M [00:11<00:05, 4.94MB/s]
+ 42%|####1 | 17.2M/41.5M [00:12<00:05, 4.48MB/s]
+ 44%|####3 | 18.2M/41.5M [00:12<00:05, 4.78MB/s]
+ 46%|####6 | 19.3M/41.5M [00:12<00:04, 5.81MB/s]
+ 49%|####9 | 20.3M/41.5M [00:12<00:03, 6.92MB/s]
+ 51%|##### | 21.1M/41.5M [00:12<00:03, 6.40MB/s]
+ 52%|#####2 | 21.8M/41.5M [00:12<00:03, 5.69MB/s]
+ 55%|#####4 | 22.7M/41.5M [00:13<00:03, 5.66MB/s]
+ 58%|#####7 | 24.0M/41.5M [00:13<00:02, 6.25MB/s]
+ 61%|###### | 25.3M/41.5M [00:13<00:02, 6.70MB/s]
+ 64%|######4 | 26.7M/41.5M [00:13<00:02, 7.19MB/s]
+ 68%|######7 | 28.2M/41.5M [00:13<00:01, 7.66MB/s]
+ 71%|#######1 | 29.6M/41.5M [00:13<00:01, 7.88MB/s]
+ 75%|#######5 | 31.1M/41.5M [00:14<00:01, 8.03MB/s]
+ 79%|#######8 | 32.6M/41.5M [00:14<00:01, 8.23MB/s]
+ 82%|########2 | 34.1M/41.5M [00:14<00:00, 8.33MB/s]
+ 86%|########5 | 35.6M/41.5M [00:14<00:00, 8.31MB/s]
+ 89%|########9 | 37.1M/41.5M [00:14<00:00, 9.61MB/s]
+ 92%|#########2| 38.3M/41.5M [00:14<00:00, 10.4MB/s]
+ 95%|#########5| 39.4M/41.5M [00:15<00:00, 8.94MB/s]
+ 97%|#########7| 40.4M/41.5M [00:15<00:00, 7.95MB/s]
+100%|##########| 41.5M/41.5M [00:15<00:00, 2.85MB/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 c84e13883..83ddb5006 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.216 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.572 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download sphx-glr-download-python 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 c509aadea..969b52a0f 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -390,10 +390,11 @@ 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]
- 23%|##2 | 10.1M/44.7M [00:00<00:00, 105MB/s]
- 59%|#####9 | 26.4M/44.7M [00:00<00:00, 144MB/s]
- 96%|#########5| 42.8M/44.7M [00:00<00:00, 157MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 150MB/s]
+ 18%|#8 | 8.20M/44.7M [00:00<00:00, 83.9MB/s]
+ 36%|###6 | 16.2M/44.7M [00:00<00:00, 80.8MB/s]
+ 66%|######6 | 29.5M/44.7M [00:00<00:00, 107MB/s]
+ 89%|########9 | 39.8M/44.7M [00:00<00:00, 95.3MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 98.2MB/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 e1c7ccd00..ee5d4617d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,7 +612,7 @@ 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 8.672 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.589 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index 0fd5d68a2..c8d702836 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:33.043</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:39.340</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -311,44 +311,44 @@
<col style="width: 8%" />
</colgroup>
<tbody>
-<tr class="row-odd"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:08.672</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
+<td><p>01:07.572</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>01:08.216</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
+<td><p>01:04.589</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>00:58.153</p></td>
+<td><p>00:59.130</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:32.464</p></td>
+<td><p>00:41.597</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.813</p></td>
+<td><p>00:24.963</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:22.968</p></td>
+<td><p>00:23.728</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.053</p></td>
+<td><p>00:22.091</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:18.921</p></td>
+<td><p>00:19.843</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:14.127</p></td>
+<td><p>00:13.447</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.657</p></td>
+<td><p>00:02.380</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index d0183ca78..6bc8e40b1 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -629,7 +629,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.1979 16.1767 16.3467 16.0937 0.0742
+ 16.3130 16.2621 16.8176 16.0556 0.2160
</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 dc6091a49..1b7c08d69 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -412,17 +412,15 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 7%|6 | 11.5M/170M [00:00<00:01, 120MB/s]
- 17%|#7 | 29.4M/170M [00:00<00:00, 160MB/s]
- 26%|##6 | 44.7M/170M [00:00<00:00, 137MB/s]
- 36%|###6 | 62.0M/170M [00:00<00:00, 152MB/s]
- 45%|####5 | 77.3M/170M [00:00<00:00, 155MB/s]
- 54%|#####4 | 92.3M/170M [00:00<00:00, 143MB/s]
- 64%|######4 | 109M/170M [00:00<00:00, 153MB/s]
- 73%|#######3 | 125M/170M [00:00<00:00, 156MB/s]
- 82%|########2 | 140M/170M [00:00<00:00, 153MB/s]
- 92%|#########1| 155M/170M [00:01<00:00, 156MB/s]
-100%|##########| 170M/170M [00:01<00:00, 154MB/s]
+ 9%|9 | 16.0M/170M [00:00<00:00, 168MB/s]
+ 22%|##2 | 37.4M/170M [00:00<00:00, 201MB/s]
+ 35%|###4 | 59.1M/170M [00:00<00:00, 213MB/s]
+ 48%|####7 | 80.8M/170M [00:00<00:00, 219MB/s]
+ 61%|###### | 103M/170M [00:00<00:00, 224MB/s]
+ 73%|#######3 | 125M/170M [00:00<00:00, 224MB/s]
+ 86%|########5 | 146M/170M [00:00<00:00, 224MB/s]
+ 99%|#########8| 167M/170M [00:00<00:00, 224MB/s]
+100%|##########| 170M/170M [00:00<00:00, 220MB/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').
@@ -517,7 +515,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.809 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 0.820 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 0ed78f3ae..101dfe0db 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -453,8 +453,7 @@ 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]
- 61%|###### | 8.21M/13.6M [00:00<00:00, 86.0MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 106MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 204MB/s]
</pre></div>
</div>
</div>
@@ -543,7 +542,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3233 90.2573 94.0689 90.0885 0.4359
+ 90.2946 90.2761 90.7085 90.1167 0.0949
</pre></div>
</div>
<div class="admonition note">
@@ -582,7 +581,7 @@ 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 7.828 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.244 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 42212810f..1ac15912a 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -546,7 +546,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.0180 119.8968 124.4241 119.0212 0.6890
+ 121.6670 121.6092 123.9842 120.4591 0.5718
</pre></div>
</div>
<div class="admonition note">
@@ -574,7 +574,7 @@ 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 52.154 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.431 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 861a799f7..906364ffe 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -485,7 +485,7 @@ 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 16.584 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 13.142 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index e3233c934..900693c97 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -417,24 +417,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 2%|2 | 2979/132723 [00:00<00:04, 29784.06KB/s]
- 5%|4 | 6292/132723 [00:00<00:03, 31684.76KB/s]
- 9%|9 | 12387/132723 [00:00<00:02, 45029.64KB/s]
- 15%|#5 | 19937/132723 [00:00<00:01, 57047.30KB/s]
- 21%|## | 27818/132723 [00:00<00:01, 64889.36KB/s]
- 27%|##7 | 35946/132723 [00:00<00:01, 70459.09KB/s]
- 33%|###3 | 44125/132723 [00:00<00:01, 74158.71KB/s]
- 39%|###9 | 52342/132723 [00:00<00:01, 76707.00KB/s]
- 46%|####5 | 60551/132723 [00:00<00:00, 78387.93KB/s]
- 52%|#####1 | 68813/132723 [00:01<00:00, 79691.15KB/s]
- 58%|#####7 | 76964/132723 [00:01<00:00, 80244.50KB/s]
- 64%|######4 | 85156/132723 [00:01<00:00, 80749.43KB/s]
- 70%|####### | 93348/132723 [00:01<00:00, 81102.50KB/s]
- 76%|#######6 | 101524/132723 [00:01<00:00, 81299.17KB/s]
- 83%|########2 | 109738/132723 [00:01<00:00, 81548.70KB/s]
- 89%|########8 | 117914/132723 [00:01<00:00, 81602.36KB/s]
- 95%|#########4| 126075/132723 [00:01<00:00, 79626.76KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 74144.83KB/s]
+ 5%|5 | 6665/132723 [00:00<00:01, 66641.17KB/s]
+ 12%|#1 | 15330/132723 [00:00<00:01, 78402.88KB/s]
+ 18%|#8 | 23909/132723 [00:00<00:01, 81773.71KB/s]
+ 25%|##4 | 32619/132723 [00:00<00:01, 83874.15KB/s]
+ 31%|###1 | 41325/132723 [00:00<00:01, 85019.08KB/s]
+ 38%|###7 | 50057/132723 [00:00<00:00, 85796.22KB/s]
+ 44%|####4 | 58824/132723 [00:00<00:00, 86400.90KB/s]
+ 51%|##### | 67571/132723 [00:00<00:00, 86737.88KB/s]
+ 58%|#####7 | 76351/132723 [00:00<00:00, 87066.53KB/s]
+ 64%|######4 | 85058/132723 [00:01<00:00, 87001.55KB/s]
+ 71%|####### | 93825/132723 [00:01<00:00, 87201.58KB/s]
+ 77%|#######7 | 102594/132723 [00:01<00:00, 87348.41KB/s]
+ 84%|########3 | 111417/132723 [00:01<00:00, 87612.31KB/s]
+ 91%|######### | 120179/132723 [00:01<00:00, 87589.94KB/s]
+ 97%|#########7| 128939/132723 [00:01<00:00, 87483.14KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 85859.92KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -477,7 +475,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.635 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 23.969 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index aeb564d48..a3046aa76 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:30.951</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:32.914</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -312,31 +312,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:58.809</p></td>
+<td><p>03:00.820</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:23.635</p></td>
+<td><p>02:23.969</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:52.154</p></td>
+<td><p>01:53.431</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:16.584</p></td>
+<td><p>01:13.142</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:07.828</p></td>
+<td><p>01:08.244</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.742</p></td>
+<td><p>00:30.776</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.193</p></td>
+<td><p>00:22.526</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index db0e1965e..10592fa10 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -585,7 +585,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipb45f2be3-2555-43eb-b14e-f49412a1b804 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.zip5afb26b7-b727-419c-9f87-739b3c98352b from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
</pre></div>
</div>
<p>It’s easy to execute MobileNet with native TVM:</p>
diff --git a/docs/how_to/extend_tvm/sg_execution_times.html b/docs/how_to/extend_tvm/sg_execution_times.html
index eea35d085..5d4cdc71b 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.436</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:41.438</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,19 +312,19 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.237</p></td>
+<td><p>00:38.188</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.250</p></td>
+<td><p>00:02.298</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.941</p></td>
+<td><p>00:00.946</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 43ba02a0e..a9920a852 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -488,10 +488,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 7012us [7012us] (46.31%; 46.31%)
-FoldScaleAxis: 8129us [7us] (53.69%; 53.69%)
- FoldConstant: 8122us [1634us] (53.65%; 99.92%)
- InferType: 6488us [6488us] (42.85%; 79.88%)
+InferType: 7204us [7204us] (46.14%; 46.14%)
+FoldScaleAxis: 8410us [9us] (53.86%; 53.86%)
+ FoldConstant: 8401us [1606us] (53.80%; 99.89%)
+ InferType: 6796us [6796us] (43.52%; 80.89%)
</pre></div>
</div>
</div>
@@ -513,10 +513,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6628us [6628us] (44.87%; 44.87%)
-FoldScaleAxis: 8143us [6us] (55.13%; 55.13%)
- FoldConstant: 8137us [1672us] (55.09%; 99.93%)
- InferType: 6465us [6465us] (43.77%; 79.45%)
+InferType: 6617us [6617us] (45.31%; 45.31%)
+FoldScaleAxis: 7986us [5us] (54.69%; 54.69%)
+ FoldConstant: 7981us [1612us] (54.65%; 99.94%)
+ InferType: 6369us [6369us] (43.61%; 79.80%)
</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 7f4835a15..984988168 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -537,7 +537,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.151550 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.210778 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index cbed2ee70..6cce9abe4 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -879,7 +879,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.319113 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 7.005482 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 a4d53a961..cffd0f5fa 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -434,8 +434,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019108
-Baseline: 3.456533
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019229
+Baseline: 3.267013
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -495,7 +495,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.317625
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.317688
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -562,7 +562,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.344836
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.347051
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118763
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.120966
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -706,7 +706,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110642
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.111611
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -792,7 +792,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111169
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111472
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -882,7 +882,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145670
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145327
</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 248e65374..314e6ee06 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.081</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.613</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.812</p></td>
+<td><p>00:32.261</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.212</p></td>
+<td><p>00:01.292</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.057</p></td>
+<td><p>00:01.060</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index 970bd5f89..2de928484 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:20.119</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:17.770</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>02:41.682</p></td>
+<td><p>02:36.362</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.011</p></td>
+<td><p>01:22.625</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:43.386</p></td>
+<td><p>00:43.936</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:16.745</p></td>
+<td><p>00:17.194</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.722</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
+<td><p>00:08.865</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.572</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
+<td><p>00:08.789</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 920d847d4..4a5333d38 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
@@ -467,196 +467,494 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 64;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [768]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[7] = 0f32
- for (rc.outer.outer: int32, 0, 16) {
- for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (rc.outer.outer*288)
- let cse_var_2: int32 = (ry.outer.outer*7)
- let cse_var_1: int32 = (ry.outer.outer*3)
- {
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[(threadIdx.x_1*4)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((t [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 2), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 2), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - 8)], 0f [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 3)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 3), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 3), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - 8)], 0f [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 196), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 197)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 197), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 197), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 198)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 146)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 199)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 199), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 199), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 392), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 393)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 393), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 393), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 394)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 394), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 394), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 395)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 395), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 395), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 588), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 589)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 589), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 589), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 590)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 590), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 590), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 591)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 591), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 591), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 784), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 785)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 785), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 785), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 786)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 786), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 786), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 787)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 787), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 787), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 980), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 981)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 4), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 755)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 982)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 982), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 982), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 983)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 983), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 983), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9)) - [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1176), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1177)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1177), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1177), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1178)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1178), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1178), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1179)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 5), 7)) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 909)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1372), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1373)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1373), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1373), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1374)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1374), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 6), 9))) && (floormod(((threadIdx.x_1*4) + 6), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1374), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 6), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1375)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1375), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1375), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1568), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1569)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1569), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1569), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1570)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1570), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 4), 9))) && (floormod(((threadIdx.x_1*4) + 4), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1570), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 4), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1571)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1571), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 5), 9))) && (floormod(((threadIdx.x_1*4) + 5), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1571), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 5), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*4), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1364)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*4) + 1765)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1765), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1765), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1766)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1766), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 2), 9))) && (floormod(((threadIdx.x_1*4) + 2), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1766), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 2), 9 [...]
- pad_temp.shared_1[((threadIdx.x_1*4) + 1767)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1767), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 3), 9))) && (floormod(((threadIdx.x_1*4) + 3), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1767), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 3), 9 [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 7), 9))) && (floormod(((threadIdx.x_1*4) + 7), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1960), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 7), [...]
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1961)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*4) + 1961), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(((threadIdx.x_1*4) + 8), 9))) && (floormod(((threadIdx.x_1*4) + 8), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1961), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 8), [...]
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1962)] = @tir.if_then_else(((((ry.outer.outer + floormod((floordiv((threadIdx.x_1*4), 9) + 1), 7)) < 8) && (1 <= floormod((threadIdx.x_1*4), 9))) && (floormod((threadIdx.x_1*4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1*4), 9)*7)) + cse_var_2) + floormod((threadIdx.x_1*4), 9)) + 1518)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 14), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*4) + 1963)] = @tir.if_then_else(((((floordiv(floormod(((threadIdx.x_1*4) + 1963), 63), 9) + ry.outer.outer) < 8) && (1 <= floormod(((threadIdx.x_1*4) + 1), 9))) && (floormod(((threadIdx.x_1*4) + 1), 9) < 8)), data[((((cse_var_4 + (floordiv(((threadIdx.x_1*4) + 1963), 9)*7)) + cse_var_2) + floormod(((threadIdx.x_1*4) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1: Buffer(kernel.shared, float32, [768], [], scope="shared")[threadIdx.x_2] = kernel[(((((blockIdx.x*36864) + cse_var_3) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 49)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 49), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 49), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 98), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 98), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 147)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 147), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 17), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 196), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 196), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 245)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 245), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 245), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 294), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 343)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 343), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 343), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 392), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 392), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 441)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 441), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 19), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 490), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 490), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 539)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 539), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 539), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 588), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 637)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 637), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 637), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 686), 96)*4608)) + cse_var_3) + (floordiv(floormod((threadIdx.x_2 + 686), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49;
- if @tir.likely((threadIdx.x_2 < 33), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 735)] = kernel[((((((blockIdx.x*36864) + (floordiv((threadIdx.x_2 + 735), 96)*4608)) + cse_var_3) + (floormod((floordiv(threadIdx.x_2, 3) + 21), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- }
- for (rc.outer.inner: int32, 0, 4) {
- for (ff.outer.inner: int32, 0, 4) {
- let cse_var_7: int32 = (ff.outer.inner*2)
- let cse_var_6: int32 = (cse_var_7 + 1)
- let cse_var_5: int32 = ((ff.outer.inner*192) + (rc.outer.inner*24))
- {
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_5]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_5 + 96)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_5 + 97)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_5 + 98)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(cse_var_5 + 99)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(cse_var_5 + 100)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(cse_var_5 + 101)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(cse_var_5 + 102)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(cse_var_5 + 103)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(cse_var_5 + 104)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 9)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(cse_var_5 + 105)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 10)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(cse_var_5 + 106)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 11)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(cse_var_5 + 107)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 12)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(cse_var_5 + 108)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 13)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(cse_var_5 + 109)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 14)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(cse_var_5 + 110)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 15)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(cse_var_5 + 111)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 16)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(cse_var_5 + 112)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 17)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(cse_var_5 + 113)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 18)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 378)]*kernel.shared_1[(cse_var_5 + 114)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 19)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 379)]*kernel.shared_1[(cse_var_5 + 115)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 20)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 380)]*kernel.shared_1[(cse_var_5 + 116)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 21)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 441)]*kernel.shared_1[(cse_var_5 + 117)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 22)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 442)]*kernel.shared_1[(cse_var_5 + 118)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 23)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.outer.inner*504) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 443)]*kernel.shared_1[(cse_var_5 + 119)]))
- }
- }
- }
+ for (rc.outer.outer: int32, 0, 32) {
+ let cse_var_2: int32 = (rc.outer.outer*784)
+ let cse_var_1: int32 = (rc.outer.outer*144)
+ {
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 98)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 98), 81)) && (floormod((threadIdx.x_1 + 17), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 98), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 17), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 196), 81)) && (floormod((threadIdx.x_1 + 34), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 196), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 34), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 294)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 294), 81)) && (floormod((threadIdx.x_1 + 51), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 294), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 51), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 392), 81)) && (floormod((threadIdx.x_1 + 68), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 392), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 68), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 490)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 490), 81)) && (floormod((threadIdx.x_1 + 4), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 490), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 85), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 588), 81)) && (floormod((threadIdx.x_1 + 21), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 588), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 102), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 686)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 686), 81)) && (floormod((threadIdx.x_1 + 38), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 686), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 119), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 136), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 882)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 9) + 8), 9)) && (floormod((threadIdx.x_1 + 72), 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 882), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 8), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 980), 81)) && (floormod((threadIdx.x_1 + 8), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 980), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 170), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1078)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1078), 81)) && (floormod((threadIdx.x_1 + 25), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1078), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 187), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 204), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_1 < 22), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 1274)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 59), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1274), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 221), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
+ }
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[(((blockIdx.x*73728) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 98)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 49), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 98), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 98), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 196), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 294)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 147), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 196), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 392), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 490)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 245), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 490), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 294), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 686)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 343), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 686), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 392), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 882)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 441), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 6), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 490), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 980), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1078)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 539), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1078), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 588), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1274)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 637), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1274), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 686), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1372), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1470)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 735), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 10), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 784), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1666)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 833), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1666), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 882), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1862)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 931), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1862), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 980), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1960), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2058)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1029), 72)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 3) + 14), 48)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1078), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2156), 144), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 98;
+ if @tir.likely((threadIdx.x_2 < 50), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2254)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 2) + 1127), 72)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2254), 144), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ }
+ for (ry.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3))]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1152)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1153)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1154)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1161)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1162)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1163)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1170)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1171)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1172)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1179)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1180)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1181)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1188)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1189)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1190)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1197)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1198)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1199)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1206)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1207)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1208)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1215)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1216)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1217)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1224)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1225)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1226)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1233)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1234)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1235)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1242)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1243)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1244)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 99)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1251)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 100)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1252)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 101)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1253)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 108)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1260)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 109)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1261)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 110)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1262)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 117)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1269)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 118)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1270)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 119)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1271)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 126)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1278)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 127)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1279)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 128)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1280)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 135)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1287)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 136)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1288)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 137)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1289)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 144)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1296)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 145)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1297)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 146)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1298)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 153)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1305)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 154)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1306)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 155)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1307)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 162)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1314)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 163)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1315)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 164)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1316)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 171)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1323)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 172)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1324)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 173)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1325)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 180)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1332)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 181)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1333)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 182)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1334)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 189)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1341)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 190)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1342)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 191)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1343)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 198)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1350)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 199)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1351)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 200)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1352)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 207)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1359)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 208)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1360)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 209)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1361)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 216)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1368)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 217)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1369)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 218)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1370)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 225)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1377)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 226)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1378)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 227)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1379)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 234)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1386)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 235)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1387)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 236)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1388)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 243)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1395)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 244)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1396)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 245)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1397)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 252)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1404)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 253)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1405)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 254)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1406)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 261)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1413)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 262)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1414)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 263)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1415)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 270)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1422)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 271)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1423)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 272)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1424)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 279)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1431)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 280)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1432)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 281)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1433)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 288)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1440)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 289)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1441)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 290)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1442)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 297)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1449)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 298)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1450)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 299)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1451)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 306)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1458)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 307)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1459)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 308)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1460)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 315)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1467)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 316)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1468)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 317)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1469)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 324)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1476)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 325)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1477)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 326)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1478)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 333)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1485)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 334)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1486)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 335)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1487)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 342)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1494)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 343)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1495)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 344)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1496)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 351)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1503)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 352)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1504)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 353)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1505)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 360)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1512)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 361)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1513)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 362)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1514)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 369)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1521)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 370)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1522)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 371)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1523)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 378)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1530)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 379)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1531)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 380)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1532)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 387)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1539)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 388)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1540)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 389)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1541)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 396)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1548)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 397)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1549)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 398)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1550)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 405)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1557)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 406)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1558)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 407)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1559)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 414)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1566)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 415)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1567)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 416)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1568)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 423)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1575)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 424)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1576)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 425)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 432)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 433)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 434)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 441)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 442)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 443)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 450)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 451)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 452)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 459)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 460)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1612)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 461)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1613)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 468)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1620)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 469)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1621)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 470)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1622)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 477)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1629)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 478)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1630)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 479)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1631)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 486)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1638)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 487)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1639)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 488)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1640)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 495)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1647)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 496)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1648)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 497)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1649)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 504)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1656)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 505)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1657)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 506)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1658)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 513)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1665)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 514)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1666)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 515)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1667)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 522)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1674)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 523)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1675)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 524)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1676)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 531)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1683)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 532)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1684)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 533)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1685)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 540)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1692)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 541)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1693)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 542)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1694)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 549)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1701)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 550)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1702)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 551)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1703)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 558)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1710)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 559)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1711)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 560)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1712)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 567)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1719)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 568)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1720)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 569)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((floordiv(floormod(threadIdx.x, 49), 7)*9) + (ry.outer.inner*9)) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[(((floordiv(threadIdx.x, 49)*576) + (ry.outer.inner*3)) + 1721)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[(((blockIdx.x*392) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*8) + i1.inner)]), 0f32)
+ for (i1.inner: int32, 0, 4) {
+ compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*196)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*4)) + i1.inner) + 8)]), 0f32)
}
}
}
@@ -693,7 +991,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.263 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.346 ms
</pre></div>
</div>
</div>
@@ -722,10 +1020,10 @@ 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_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=4)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=2)
+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=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
@@ -734,19 +1032,19 @@ conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, fact
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=8)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=16)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=1)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=8)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=4)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=2)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
@@ -771,14 +1069,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=4)
+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=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=98)
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", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -796,148 +1094,453 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+extern "C" __global__ void __launch_bounds__(98) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
- __shared__ float kernel_shared[768];
+ __shared__ float pad_temp_shared[1296];
+ __shared__ float kernel_shared[2304];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
- for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
- __syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 4)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 2) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 3)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 3) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : 0.000 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 196)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 197)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 197) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : 0 [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 198)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 1) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 146)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 199)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 199) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 392)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 393)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 15) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 393) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 394)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 16) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 394) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 395)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 17) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 395) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 588)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 589)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 22) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 589) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 590)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 23) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 590) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 591)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 24) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 591) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 784)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 785)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 29) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 785) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 786)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 30) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 786) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 787)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 31) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 787) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 980)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 981)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 4) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 755)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 982)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 37) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 982) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 983)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 38) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 983) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1176)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1177)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 43) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1177) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1178)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 44) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1178) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1179)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 4) / 9) + 5) % 7)) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 909)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1372)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1373)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 50) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1373) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1374)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 51) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 6) % 9))) && ((((((int)threadIdx.x) * 4) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1374) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 6) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1375)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 52) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1375) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1568)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1569)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 57) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1569) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1570)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 58) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 4) % 9))) && ((((((int)threadIdx.x) * 4) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1570) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 4) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1571)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 59) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 5) % 9))) && ((((((int)threadIdx.x) * 4) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1571) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 5) % 9)) - 8)] [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1764)] = (((((1 <= ((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) * 4) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1364)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1765)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 1) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1765) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1766)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 2) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 2) % 9))) && ((((((int)threadIdx.x) * 4) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1766) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 2) % 9)) - 8)] : [...]
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1767)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 3) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 3) % 9))) && ((((((int)threadIdx.x) * 4) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1767) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 3) % 9)) - 8)] : [...]
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1960)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 7) % 9))) && ((((((int)threadIdx.x) * 4) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 7) % 9)) - 8)] [...]
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1961)] = (((((1 <= (((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 4) + 8) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((((int)threadIdx.x) * 4) + 8) % 9))) && ((((((int)threadIdx.x) * 4) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1961) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 8) % 9)) - 8)] [...]
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1962)] = (((((ry_outer_outer + (((((int)threadIdx.x) * 4) / 9) + 1)) < 8) && (1 <= ((((int)threadIdx.x) * 4) % 9))) && (((((int)threadIdx.x) * 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 4) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) * 4) % 9)) + 1518)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 14) {
- pad_temp_shared[((((int)threadIdx.x) * 4) + 1963)] = (((((((((((int)threadIdx.x) * 4) + 10) % 63) / 9) + ry_outer_outer) < 8) && (1 <= (((((int)threadIdx.x) * 4) + 1) % 9))) && ((((((int)threadIdx.x) * 4) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 4) + 1963) / 9) * 7)) + (ry_outer_outer * 7)) + (((((int)threadIdx.x) * 4) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) * 36864) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 49)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 49) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 49) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 98)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 98) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 2) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 147)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 147) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 17) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 245)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 245) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 53) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 294)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 294) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 2) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 343)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 343) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 55) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 441)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 441) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 19) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 490)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 490) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 10) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 539)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 539) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 59) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 4) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 637)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 637) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 61) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 686)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 686) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 14) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 33) {
- kernel_shared[(((int)threadIdx.x) + 735)] = kernel[((((((((int)blockIdx.x) * 36864) + (((((int)threadIdx.x) + 735) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) / 3) + 21) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- }
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 4; ++ff_outer_inner) {
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((ff_outer_inner * 192) + (rc_outer_inner * 24))]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[(((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 96)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 97)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 98)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 99)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 100)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 101)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 102)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 103)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 104)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 9)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 105)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 10)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 106)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 11)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 107)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 12)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 108)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 13)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 109)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 14)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 110)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 15)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 111)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 16)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 112)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 17)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 113)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 18)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 378)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 114)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 19)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 379)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 115)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 20)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 380)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 116)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 21)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 441)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 117)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 22)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 442)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 118)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 23)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_outer_inner * 504) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 443)] * kernel_shared[(((ff_outer_inner * 192) + (rc_outer_inner * 24)) + 119)]));
- }
- }
+ for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ __syncthreads();
+ pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 98)] = (((((9 <= ((((int)threadIdx.x) + 17) % 81)) && (((((int)threadIdx.x) + 17) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 98) / 81) * 49)) + ((((((int)threadIdx.x) + 17) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((9 <= ((((int)threadIdx.x) + 34) % 81)) && (((((int)threadIdx.x) + 34) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 196) / 81) * 49)) + ((((((int)threadIdx.x) + 34) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 294)] = (((((9 <= ((((int)threadIdx.x) + 51) % 81)) && (((((int)threadIdx.x) + 51) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 294) / 81) * 49)) + ((((((int)threadIdx.x) + 51) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 490)] = (((((9 <= ((((int)threadIdx.x) + 4) % 81)) && (((((int)threadIdx.x) + 4) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 490) / 81) * 49)) + ((((((int)threadIdx.x) + 4) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((9 <= ((((int)threadIdx.x) + 21) % 81)) && (((((int)threadIdx.x) + 21) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 686)] = (((((9 <= ((((int)threadIdx.x) + 38) % 81)) && (((((int)threadIdx.x) + 38) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 686) / 81) * 49)) + ((((((int)threadIdx.x) + 38) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 882)] = (((((1 <= (((((int)threadIdx.x) / 9) + 8) % 9)) && (((((int)threadIdx.x) + 72) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 882) / 81) * 49)) + ((((((int)threadIdx.x) / 9) + 8) % 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((9 <= ((((int)threadIdx.x) + 8) % 81)) && (((((int)threadIdx.x) + 8) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 980) / 81) * 49)) + ((((((int)threadIdx.x) + 8) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1078)] = (((((9 <= ((((int)threadIdx.x) + 25) % 81)) && (((((int)threadIdx.x) + 25) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1078) / 81) * 49)) + ((((((int)threadIdx.x) + 25) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 22) {
+ pad_temp_shared[(((int)threadIdx.x) + 1274)] = ((((((int)threadIdx.x) < 13) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1274) / 81) * 49)) + ((((((int)threadIdx.x) + 59) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((int)blockIdx.x) * 73728) + (rc_outer_outer * 144)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 98)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 98) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 98) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 196) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 52) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 294)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 294) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 2) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 104) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 490)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 490) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 58) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 588) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 4) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 686)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 686) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 110) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 64) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 882)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 882) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 6) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 980) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 116) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1078)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1078) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 70) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 8) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1274)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1274) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 122) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1372) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 76) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1470)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1470) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 10) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 128) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1666)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1666) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 82) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1764) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 12) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1862)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1862) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 134) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 88) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2058)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2058) / 144) * 4608)) + (rc_outer_outer * 144)) + (((((int)threadIdx.x) / 3) + 14) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2156) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 140) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ if (((int)threadIdx.x) < 50) {
+ kernel_shared[(((int)threadIdx.x) + 2254)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 2254) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) + 94) % 144) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ }
+ __syncthreads();
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3))]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1152)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1153)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1154)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1161)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1162)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1163)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1170)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1171)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1172)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1179)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1180)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1181)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1188)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1189)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1190)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1197)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1198)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1199)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1206)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1207)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1208)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1215)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1216)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1217)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1224)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1225)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1226)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1233)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1234)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1235)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1242)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1243)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1244)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 99)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1251)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 100)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1252)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 101)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1253)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 108)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1260)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 109)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1261)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 110)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1262)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 117)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1269)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 118)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1270)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 119)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1271)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 126)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1278)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 127)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1279)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 128)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1280)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 135)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1287)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 136)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1288)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 137)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1289)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 144)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1296)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 145)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1297)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 146)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1298)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 153)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1305)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 154)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1306)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 155)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1307)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 162)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1314)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 163)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1315)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 164)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1316)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 171)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1323)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 172)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1324)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 173)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1325)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 180)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1332)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 181)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1333)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 182)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1334)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 189)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1341)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 190)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1342)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 191)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1343)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 198)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1350)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 199)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1351)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 200)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1352)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 207)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1359)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 208)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1360)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 209)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1361)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 216)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1368)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 217)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1369)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 218)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1370)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 225)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1377)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 226)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1378)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 227)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1379)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 234)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1386)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 235)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1387)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 236)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1388)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 243)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1395)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 244)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1396)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 245)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1397)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 252)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1404)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 253)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1405)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 254)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1406)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 261)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1413)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 262)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1414)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 263)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1415)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 270)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1422)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 271)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1423)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 272)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1424)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 279)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1431)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 280)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1432)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 281)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1433)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 288)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1440)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 289)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1441)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 290)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1442)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 297)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1449)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 298)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1450)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 299)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1451)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 306)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1458)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 307)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1459)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 308)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1460)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 315)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1467)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 316)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1468)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 317)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1469)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 324)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1476)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 325)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1477)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 326)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1478)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 333)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1485)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 334)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1486)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 335)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1487)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 342)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1494)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 343)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1495)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 344)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1496)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 351)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1503)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 352)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1504)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 353)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1505)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 360)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1512)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 361)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1513)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 362)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1514)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 369)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1521)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 370)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1522)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 371)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1523)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 378)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1530)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 379)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1531)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 380)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1532)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 387)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1539)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 388)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1540)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 389)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1541)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 396)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1548)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 397)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1549)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 398)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1550)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 405)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1557)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 406)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1558)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 407)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1559)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 414)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1566)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 415)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1567)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 416)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1568)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 423)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1575)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 424)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1576)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 425)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 432)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 433)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 434)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 441)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 442)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 443)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 450)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 451)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 452)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 459)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 460)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1612)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 461)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1613)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 468)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1620)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 469)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1621)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 470)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1622)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 477)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1629)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 478)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1630)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 479)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1631)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 486)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1638)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 487)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1639)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 488)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1640)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 495)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1647)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 496)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1648)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 497)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1649)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 504)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1656)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 505)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1657)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 506)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1658)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 513)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1665)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 514)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1666)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 515)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1667)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 522)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1674)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 523)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1675)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 524)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1676)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 531)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1683)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 532)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1684)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 533)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1685)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 540)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1692)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 541)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1693)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 542)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1694)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 549)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1701)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 550)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1702)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 551)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1703)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 558)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1710)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 559)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1711)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 560)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1712)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 567)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1719)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 568)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1720)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 569)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((((int)threadIdx.x) % 49) / 7) * 9) + (ry_outer_inner * 9)) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[((((((int)threadIdx.x) / 49) * 576) + (ry_outer_inner * 3)) + 1721)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 392) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 8) + i1_inner)]), 0.000000e+00f);
+ for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
+ compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 196)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 4)) + i1_inner) + 8)]), 0.000000e+00f);
}
}
</pre></div>
@@ -974,7 +1577,7 @@ 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 41.682 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.362 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index 0de933b76..7b73f10d5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -882,7 +882,7 @@ 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)
- 10.1698 10.2085 10.2262 10.0747 0.0677
+ 9.7312 9.7496 9.7531 9.6909 0.0285
</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 ed7e7fed9..8e556eba5 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 755.8342 756.1985 756.3605 754.9437 0.6332
+ 765.8382 765.6893 767.0312 764.7941 0.9193
</pre></div>
</div>
</div>
@@ -923,7 +923,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.011 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 22.625 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index 4097fb97b..96ef205af 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -601,75 +601,78 @@ 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_6: placeholder_15: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_16: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_19: Buffer(placeholder_12, int32, [4916], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 256) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [256]), storage_scope = global {
- for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = ((i.inner.init*32) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [256], [])[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_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i.inner*32) + (nb_j.inner*16))
- let cse_var_19: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_18: int32 = ((floordiv(i0.outer.i1.outer.fused, 16)*2048) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_20 + 9)
- let cse_var_16: int32 = (cse_var_20 + 8)
- let cse_var_15: int32 = (cse_var_20 + 7)
- let cse_var_14: int32 = (cse_var_20 + 6)
- let cse_var_13: int32 = (cse_var_20 + 5)
- let cse_var_12: int32 = (cse_var_20 + 4)
- let cse_var_11: int32 = (cse_var_20 + 3)
- let cse_var_10: int32 = (cse_var_20 + 2)
- let cse_var_9: int32 = (cse_var_20 + 15)
- let cse_var_8: int32 = (cse_var_20 + 14)
- let cse_var_7: int32 = (cse_var_20 + 13)
- let cse_var_6: int32 = (cse_var_20 + 12)
- let cse_var_5: int32 = (cse_var_20 + 11)
- let cse_var_4: int32 = (cse_var_20 + 10)
- let cse_var_3: int32 = (cse_var_20 + 1)
+ preflattened_buffer_map = {compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), placeholder_6: placeholder_17: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_19: Buffer(placeholder_14, float32, [128, 512], [])} {
+ for (i0.outer: int32, 0, 32) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [128]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 2) {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 2) {
+ let cse_var_1: int32 = (((i.outer.inner*64) + (i.inner.init*32)) + (nb_j.inner*16))
{
- compute_5[cse_var_20] = (compute_5[cse_var_20] + (placeholder_1[((placeholder_3[cse_var_19]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_19]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_19] + elem_idx)])], 0f32)))
+ 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_2: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
+ for (i.inner: int32, 0, 2) {
+ let cse_var_21: int32 = (elem_idx*16)
+ let cse_var_20: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_19: int32 = (((i0.outer*1024) + (i.outer.inner*512)) + (i.inner*256))
+ let cse_var_18: int32 = (((i.outer.inner*64) + (i.inner*32)) + (nb_j.inner*16))
+ let cse_var_17: int32 = (cse_var_18 + 9)
+ let cse_var_16: int32 = (cse_var_18 + 8)
+ let cse_var_15: int32 = (cse_var_18 + 7)
+ let cse_var_14: int32 = (cse_var_18 + 6)
+ let cse_var_13: int32 = (cse_var_18 + 5)
+ let cse_var_12: int32 = (cse_var_18 + 4)
+ let cse_var_11: int32 = (cse_var_18 + 3)
+ let cse_var_10: int32 = (cse_var_18 + 2)
+ let cse_var_9: int32 = (cse_var_18 + 15)
+ let cse_var_8: int32 = (cse_var_18 + 14)
+ let cse_var_7: int32 = (cse_var_18 + 13)
+ let cse_var_6: int32 = (cse_var_18 + 12)
+ let cse_var_5: int32 = (cse_var_18 + 11)
+ let cse_var_4: int32 = (cse_var_18 + 10)
+ let cse_var_3: int32 = (cse_var_18 + 1)
+ {
+ compute_5[cse_var_18] = (compute_5[cse_var_18] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_19 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
+ }
}
}
}
}
- for (i0.inner: int32, 0, 8) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*4096) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
+ for (i0.inner: int32, 0, 4) {
+ let cse_var_22: int32 = (((i0.outer*2048) + (i0.inner*512)) + (i1.outer*32))
compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
}
}
@@ -708,7 +711,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.908 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 3.114 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 2c9dfb588..5833b6754 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.107</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.568</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:43.077</p></td>
+<td><p>00:43.535</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.016</p></td>
+<td><p>00:00.020</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
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 b48aff18d..73c42b3f8 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1145,8 +1145,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 42.35/42.35 result: MeasureResult(costs=(0.005466817526315789,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6181449890136719, timestamp=1655604934.3202896) [('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: 0.00/42.35 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.38/42.38 result: MeasureResult(costs=(0.005462087578947368,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6693322658538818, timestamp=1655733478.5661983) [('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: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1269,7 +1269,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1392,7 +1392,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1515,7 +1515,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.38 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
@@ -1533,7 +1533,7 @@ No: 10 GFLOPS: 0.00/42.35 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: 0.00/42.35 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1656,7 +1656,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1779,7 +1779,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1902,7 +1902,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2025,7 +2025,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2148,7 +2148,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2271,7 +2271,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2394,7 +2394,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2517,7 +2517,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/42.35 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.38 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2605,7 +2605,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f9bd2753fa2
+ 12: 0x00007f3492fe4fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2670,7 +2670,7 @@ 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: 141.88/141.88 result: MeasureResult(costs=(0.0016316605967741937,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1448559761047363, timestamp=1655604960.5619738) [('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: 144.84/144.84 result: MeasureResult(costs=(0.00159836847,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4229810237884521, timestamp=1655733505.158254) [('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,
@@ -2711,7 +2711,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.002077
+Time cost of this operator: 0.002027
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index b7d484eb4..5edbdce9d 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -559,10 +559,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.5 98.767 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.076 0.954 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.279 (1, 1, 10, 10, 3) 1 1
-Total_time - 322.477 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.3 98.75 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.103 0.963 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.925 0.287 (1, 1, 10, 10, 3) 1 1
+Total_time - 322.328 - - - -
</pre></div>
</div>
</div>
@@ -615,10 +615,10 @@ Total_time -
########## 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 302.6 99.037 (1, 3, 10, 10, 2) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.1 0.687 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.842 0.276 (1, 3, 10, 10, 1) 1 1
-Total_time - 305.542 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 327.3 98.809 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.144 0.949 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.801 0.242 (1, 3, 10, 10, 1) 1 1
+Total_time - 331.245 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 9a42583e0..50d0f70f5 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -490,7 +490,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpekj1pstw/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpzc_21d_e/images/random'
</pre></div>
</div>
</div>
@@ -550,8 +550,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpekj1pstw/images/target contains 8144 images
-/tmp/tmpekj1pstw/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpzc_21d_e/images/target contains 8144 images
+/tmp/tmpzc_21d_e/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -663,13 +663,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2106 - accuracy: 0.9272 - val_loss: 0.1392 - val_accuracy: 0.9581
+328/328 - 55s - loss: 0.2191 - accuracy: 0.9258 - val_loss: 0.1354 - val_accuracy: 0.9592
Epoch 2/3
-328/328 - 52s - loss: 0.0929 - accuracy: 0.9648 - val_loss: 0.1194 - val_accuracy: 0.9558
+328/328 - 52s - loss: 0.0967 - accuracy: 0.9633 - val_loss: 0.1141 - val_accuracy: 0.9664
Epoch 3/3
-328/328 - 52s - loss: 0.0631 - accuracy: 0.9753 - val_loss: 0.1586 - val_accuracy: 0.9520
+328/328 - 52s - loss: 0.0652 - accuracy: 0.9763 - val_loss: 0.1310 - val_accuracy: 0.9585
-<keras.callbacks.History object at 0x7f7f81a17d50>
+<keras.callbacks.History object at 0x7f2c606b3c10>
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 13.555 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 12.914 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 73c860947..218958c73 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:59.917</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:01.333</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,22 +312,22 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>04:13.555</p></td>
+<td><p>04:12.914</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:42.872</p></td>
+<td><p>00:44.863</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.490</p></td>
+<td><p>00:03.556</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><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></td>
+<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><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></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
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 70dab7714..536a3dca4 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:11.804</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.463</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.091</p></td>
+<td><p>00:09.943</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.708</p></td>
+<td><p>00:01.514</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 985162c27..54eba4c2f 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -496,7 +496,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f7f092649e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f2bd12f2830>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 70866461f..a071b89f0 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.063</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.249</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.884</p></td>
+<td><p>00:01.973</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.974</p></td>
+<td><p>00:01.003</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.518</p></td>
+<td><p>00:00.559</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.513</p></td>
+<td><p>00:00.540</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.101</p></td>
+<td><p>00:00.102</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.034</p></td>
+<td><p>00:00.033</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 17b92d067..2ac4a20e3 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/tmp4wfezi25/input0.cc'\nsource_filename = \"/tmp/tmp4wfezi25/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/tmpf_mjh9qi/input0.cc'\nsource_filename = \"/tmp/tmpf_mjh9qi/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 d703a96aa..b57b1440a 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1718,7 +1718,7 @@ 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">
@@ -1755,7 +1755,7 @@ 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 9da69fb71..717241e74 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/9bba7580b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 019c6ca9a..c04c0a94e 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/9bba7580b/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 b983b8e93..89058bb7f 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/9bba7580b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 33ac594d3..cd415bff2 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/9bba7580b/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 1ac28b762..0ca1e2d3d 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/9bba7580b/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 fc9e047e7..4817b5d7c 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/9bba7580b/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 716b6e095..82e47bdba 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/9bba7580b/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 52d688ccb..33d45d444 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/9bba7580b/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 d0f4d7380..8d844b422 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/9bba7580b/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 50bf1e2ed..834f8b87d 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/9bba7580b/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 43eb98267..6bdfec92e 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/9bba7580b/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 4a19647df..d64ede642 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/9bba7580b/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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 4c0170c4c..5984403da 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/9bba7580b/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/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/9bba7580b/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index 0348e01fd..13bd1b015 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index 149fc6877..99c5edb9f 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index c9683f14a..4ce9899d8 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 3b615c090..97faf75c5 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index df268cfd5..c7592897a 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 8f6bbfc2f..a53ad64d3 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 7e489c999..4cbb299a5 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 47890d213..91e1f1c68 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index 6fc29151d..1f293d38d 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 2dfb3667e..8751b2a70 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index 7b8fabc4c..f46721c1b 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/9bba7580b/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/8bf6cd580/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index d327156ec..72f2dc04f 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 6d5db3bf7..b4aad9788 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.158</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.531</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -312,7 +312,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:21.151</p></td>
+<td><p>00:21.524</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 5a4c14fe0..98e11a79e 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -547,7 +547,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.98s!
+resnet18_v1 inference graph built in 23.80s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index 7aeb04fbe..2ee5e1a2d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -565,7 +565,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.94s!
+yolov3-tiny inference graph built in 16.41s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index 667a2c9eb..fa72c4ffd 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:31.167</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:32.878</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:47.988</p></td>
+<td><p>00:48.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.179</p></td>
+<td><p>00:44.115</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index e67da84dc..5c11dea9f 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.155</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.275</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.773</p></td>
+<td><p>00:02.858</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.382</p></td>
+<td><p>00:00.417</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 8021ca934..c9bc14d86 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.670</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.765</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.344</p></td>
+<td><p>00:00.398</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.326</p></td>
+<td><p>00:00.367</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 9c34d9f94..17d5d49b5 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -545,7 +545,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.251 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.791 ms
</pre></div>
</div>
</div>
@@ -619,6 +619,7 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.970 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_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">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index 1b2027f6b..357d7b437 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -641,16 +641,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.57/10.57 result: MeasureResult(costs=(0.025385777399999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5395407676696777, timestamp=1655603786.3160706) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.94/10.57 result: MeasureResult(costs=(0.09143734220000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6145367622375488, timestamp=1655603787.9458416) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.75/11.75 result: MeasureResult(costs=(0.0228490836,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5479917526245117, timestamp=1655603788.979352) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.85/11.75 result: MeasureResult(costs=(0.14544340039999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4420828819274902, timestamp=1655603791.4701326) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.63/11.75 result: MeasureResult(costs=(0.0739892636,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3167030811309814, timestamp=1655603792.9196887) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.71/11.75 result: MeasureResult(costs=(0.15672989939999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.6239707469940186, timestamp=1655603796.0935812) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.87/11.75 result: MeasureResult(costs=(0.3098984232,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.078963041305542, timestamp=1655603801.717946) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.43/11.75 result: MeasureResult(costs=(0.025726249200000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5549643039703369, timestamp=1655603802.293098) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.90/11.75 result: MeasureResult(costs=(0.1411097294,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3798537254333496, timestamp=1655603804.7938366) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.78/11.75 result: MeasureResult(costs=(0.09673240520000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6713755130767822, timestamp=1655603806.5056226) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 9.01/9.01 result: MeasureResult(costs=(0.029779154000000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6099598407745361, timestamp=1655732313.546892) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.49/9.01 result: MeasureResult(costs=(0.10785634460000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8482446670532227, timestamp=1655732315.4355016) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.77/11.77 result: MeasureResult(costs=(0.022798908599999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5790083408355713, timestamp=1655732316.4734576) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.66/11.77 result: MeasureResult(costs=(0.1618017972,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7039570808410645, timestamp=1655732319.7315443) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.57/11.77 result: MeasureResult(costs=(0.07527840820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3339087963104248, timestamp=1655732321.1948173) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.82/11.77 result: MeasureResult(costs=(0.1474598624,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.478830575942993, timestamp=1655732324.2326336) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.84/11.77 result: MeasureResult(costs=(0.3209505134,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.256069898605347, timestamp=1655732329.534552) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.24/11.77 result: MeasureResult(costs=(0.0262151928,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.562058687210083, timestamp=1655732330.1164155) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.64/11.77 result: MeasureResult(costs=(0.1631957674,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.7320749759674072, timestamp=1655732332.969159) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.47/11.77 result: MeasureResult(costs=(0.10880448839999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8636035919189453, timestamp=1655732334.873018) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index f7322be65..e78d5d221 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -523,7 +523,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 497.4624736399983, 'median': 497.29978324999706, 'std': 1.4899553090543256}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 500.9948443700159, 'median': 501.13534275001257, 'std': 0.7143444638204062}
</pre></div>
</div>
</div>
@@ -678,179 +678,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.34/ 17.34 GFLOPS | Progress: (4/20) | 6.15 s
-[Task 1/25] Current/Best: 6.17/ 17.34 GFLOPS | Progress: (8/20) | 9.00 s
-[Task 1/25] Current/Best: 11.34/ 22.82 GFLOPS | Progress: (12/20) | 11.43 s
-[Task 1/25] Current/Best: 16.72/ 22.83 GFLOPS | Progress: (16/20) | 13.10 s
-[Task 1/25] Current/Best: 11.61/ 23.94 GFLOPS | Progress: (20/20) | 14.83 s Done.
+[Task 1/25] Current/Best: 17.40/ 17.40 GFLOPS | Progress: (4/20) | 6.29 s
+[Task 1/25] Current/Best: 6.16/ 17.40 GFLOPS | Progress: (8/20) | 9.21 s
+[Task 1/25] Current/Best: 11.53/ 22.67 GFLOPS | Progress: (12/20) | 11.67 s
+[Task 1/25] Current/Best: 16.69/ 22.67 GFLOPS | Progress: (16/20) | 13.37 s
+[Task 1/25] Current/Best: 11.59/ 23.79 GFLOPS | Progress: (20/20) | 15.12 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.22/ 12.83 GFLOPS | Progress: (4/20) | 3.76 s
-[Task 2/25] Current/Best: 13.99/ 17.67 GFLOPS | Progress: (8/20) | 5.04 s
-[Task 2/25] Current/Best: 21.12/ 21.12 GFLOPS | Progress: (12/20) | 6.39 s
-[Task 2/25] Current/Best: 12.85/ 21.12 GFLOPS | Progress: (16/20) | 7.67 s
-[Task 2/25] Current/Best: 10.10/ 21.12 GFLOPS | Progress: (20/20) | 9.47 s Done.
+[Task 2/25] Current/Best: 12.21/ 12.81 GFLOPS | Progress: (4/20) | 3.81 s
+[Task 2/25] Current/Best: 14.14/ 18.28 GFLOPS | Progress: (8/20) | 5.13 s
+[Task 2/25] Current/Best: 21.19/ 21.19 GFLOPS | Progress: (12/20) | 6.47 s
+[Task 2/25] Current/Best: 13.16/ 21.19 GFLOPS | Progress: (16/20) | 7.75 s
+[Task 2/25] Current/Best: 19.80/ 21.19 GFLOPS | Progress: (20/20) | 9.34 s Done.
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.83 s
-[Task 3/25] Current/Best: 15.53/ 16.84 GFLOPS | Progress: (8/20) | 7.77 s
-[Task 3/25] Current/Best: 14.87/ 16.84 GFLOPS | Progress: (12/20) | 9.47 s
-[Task 3/25] Current/Best: 7.21/ 23.77 GFLOPS | Progress: (16/20) | 11.38 s
-[Task 3/25] Current/Best: 12.59/ 23.77 GFLOPS | Progress: (20/20) | 15.91 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.50 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.52/ 16.86 GFLOPS | Progress: (8/20) | 7.79 s
+[Task 3/25] Current/Best: 14.80/ 16.86 GFLOPS | Progress: (12/20) | 9.52 s
+[Task 3/25] Current/Best: 7.18/ 23.76 GFLOPS | Progress: (16/20) | 11.44 s
+[Task 3/25] Current/Best: 12.48/ 23.76 GFLOPS | Progress: (20/20) | 15.97 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.56/ 20.28 GFLOPS | Progress: (4/20) | 2.34 s
-[Task 4/25] Current/Best: 6.84/ 20.28 GFLOPS | Progress: (8/20) | 6.68 s
-[Task 4/25] Current/Best: 21.75/ 21.75 GFLOPS | Progress: (12/20) | 11.24 s
-[Task 4/25] Current/Best: 17.29/ 21.75 GFLOPS | Progress: (16/20) | 13.48 s
-[Task 4/25] Current/Best: 13.10/ 21.75 GFLOPS | Progress: (20/20) | 15.51 s Done.
+[Task 4/25] Current/Best: 9.55/ 20.35 GFLOPS | Progress: (4/20) | 2.40 s
+[Task 4/25] Current/Best: 6.44/ 20.35 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 4/25] Current/Best: 21.80/ 21.80 GFLOPS | Progress: (12/20) | 11.17 s
+[Task 4/25] Current/Best: 17.02/ 21.80 GFLOPS | Progress: (16/20) | 13.38 s
+[Task 4/25] Current/Best: 13.44/ 21.80 GFLOPS | Progress: (20/20) | 15.28 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.37/ 10.21 GFLOPS | Progress: (4/20) | 2.58 s
-[Task 5/25] Current/Best: 11.67/ 12.51 GFLOPS | Progress: (8/20) | 4.64 s
-[Task 5/25] Current/Best: 10.73/ 18.07 GFLOPS | Progress: (12/20) | 7.73 s
-[Task 5/25] Current/Best: 11.50/ 22.64 GFLOPS | Progress: (16/20) | 9.16 s
-[Task 5/25] Current/Best: 11.82/ 22.64 GFLOPS | Progress: (20/20) | 11.03 s Done.
+[Task 5/25] Current/Best: 9.83/ 10.34 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 5/25] Current/Best: 11.75/ 12.91 GFLOPS | Progress: (8/20) | 4.61 s
+[Task 5/25] Current/Best: 11.08/ 17.78 GFLOPS | Progress: (12/20) | 7.73 s
+[Task 5/25] Current/Best: 12.00/ 22.48 GFLOPS | Progress: (16/20) | 9.14 s
+[Task 5/25] Current/Best: 12.04/ 22.48 GFLOPS | Progress: (20/20) | 10.99 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.14/ 20.74 GFLOPS | Progress: (4/20) | 3.97 s
-[Task 6/25] Current/Best: 18.96/ 20.74 GFLOPS | Progress: (8/20) | 5.73 s
-[Task 6/25] Current/Best: 13.33/ 20.74 GFLOPS | Progress: (12/20) | 7.66 s
-[Task 6/25] Current/Best: 19.97/ 20.74 GFLOPS | Progress: (16/20) | 9.88 s
-[Task 6/25] Current/Best: 3.73/ 20.74 GFLOPS | Progress: (20/20) | 12.42 s Done.
+[Task 6/25] Current/Best: 12.13/ 20.82 GFLOPS | Progress: (4/20) | 3.95 s
+[Task 6/25] Current/Best: 19.01/ 20.82 GFLOPS | Progress: (8/20) | 5.71 s
+[Task 6/25] Current/Best: 12.99/ 20.82 GFLOPS | Progress: (12/20) | 7.63 s
+[Task 6/25] Current/Best: 19.82/ 20.82 GFLOPS | Progress: (16/20) | 9.87 s
+[Task 6/25] Current/Best: 3.76/ 20.82 GFLOPS | Progress: (20/20) | 12.40 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.17/ 12.90 GFLOPS | Progress: (4/20) | 3.51 s
-[Task 7/25] Current/Best: 20.19/ 21.05 GFLOPS | Progress: (8/20) | 5.02 s
-[Task 7/25] Current/Best: 15.85/ 21.05 GFLOPS | Progress: (12/20) | 6.94 s
-[Task 7/25] Current/Best: 12.23/ 21.05 GFLOPS | Progress: (16/20) | 9.00 s
-[Task 7/25] Current/Best: 6.31/ 21.05 GFLOPS | Progress: (20/20) | 11.48 s Done.
+[Task 7/25] Current/Best: 11.16/ 12.82 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 7/25] Current/Best: 20.35/ 21.18 GFLOPS | Progress: (8/20) | 5.15 s
+[Task 7/25] Current/Best: 15.98/ 21.18 GFLOPS | Progress: (12/20) | 7.10 s
+[Task 7/25] Current/Best: 12.26/ 21.18 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 7/25] Current/Best: 6.41/ 21.74 GFLOPS | Progress: (20/20) | 11.62 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.90/ 13.85 GFLOPS | Progress: (4/20) | 2.86 s
-[Task 8/25] Current/Best: 9.45/ 13.85 GFLOPS | Progress: (8/20) | 7.74 s
-[Task 8/25] Current/Best: 12.57/ 13.85 GFLOPS | Progress: (12/20) | 13.99 s
-[Task 8/25] Current/Best: 18.89/ 18.89 GFLOPS | Progress: (16/20) | 16.07 s
-[Task 8/25] Current/Best: 19.83/ 19.83 GFLOPS | Progress: (20/20) | 22.51 s Done.
+[Task 8/25] Current/Best: 10.50/ 14.53 GFLOPS | Progress: (4/20) | 2.88 s
+[Task 8/25] Current/Best: 9.81/ 14.53 GFLOPS | Progress: (8/20) | 7.67 s
+[Task 8/25] Current/Best: 13.36/ 14.53 GFLOPS | Progress: (12/20) | 13.77 s
+[Task 8/25] Current/Best: 18.98/ 18.98 GFLOPS | Progress: (16/20) | 15.87 s
+[Task 8/25] Current/Best: 19.74/ 19.74 GFLOPS | Progress: (20/20) | 22.41 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.34/ 15.31 GFLOPS | Progress: (4/20) | 11.88 s
-[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.67 s
-[Task 9/25] Current/Best: 8.32/ 23.41 GFLOPS | Progress: (12/20) | 16.08 s
-[Task 9/25] Current/Best: 17.84/ 23.41 GFLOPS | Progress: (16/20) | 18.68 s
-[Task 9/25] Current/Best: 9.00/ 23.41 GFLOPS | Progress: (20/20) | 26.32 s
+[Task 9/25] Current/Best: 14.24/ 15.66 GFLOPS | Progress: (4/20) | 11.96 s
+[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.71 s
+[Task 9/25] Current/Best: 8.25/ 23.41 GFLOPS | Progress: (12/20) | 16.11 s
+[Task 9/25] Current/Best: 17.97/ 23.41 GFLOPS | Progress: (16/20) | 18.78 s
+[Task 9/25] Current/Best: 8.89/ 23.41 GFLOPS | Progress: (20/20) | 26.57 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (4/20) | 2.55 s
-[Task 10/25] Current/Best: 15.52/ 18.28 GFLOPS | Progress: (8/20) | 4.13 s
-[Task 10/25] Current/Best: 12.32/ 19.04 GFLOPS | Progress: (12/20) | 5.65 s
-[Task 10/25] Current/Best: 19.09/ 20.61 GFLOPS | Progress: (16/20) | 6.76 s
-[Task 10/25] Current/Best: 8.85/ 20.61 GFLOPS | Progress: (20/20) | 8.29 s Done.
+[Task 10/25] Current/Best: 18.57/ 18.57 GFLOPS | Progress: (4/20) | 2.56 s
+[Task 10/25] Current/Best: 15.61/ 18.57 GFLOPS | Progress: (8/20) | 4.15 s
+[Task 10/25] Current/Best: 12.80/ 19.00 GFLOPS | Progress: (12/20) | 5.67 s
+[Task 10/25] Current/Best: 19.15/ 20.32 GFLOPS | Progress: (16/20) | 6.79 s
+[Task 10/25] Current/Best: 8.91/ 20.32 GFLOPS | Progress: (20/20) | 8.35 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.28/ 18.09 GFLOPS | Progress: (4/20) | 3.27 s
-[Task 11/25] Current/Best: 16.75/ 18.09 GFLOPS | Progress: (8/20) | 6.03 s
-[Task 11/25] Current/Best: 16.12/ 18.09 GFLOPS | Progress: (12/20) | 8.10 s
-[Task 11/25] Current/Best: 13.45/ 21.19 GFLOPS | Progress: (16/20) | 10.88 s
-[Task 11/25] Current/Best: 19.33/ 21.19 GFLOPS | Progress: (20/20) | 12.92 s Done.
+[Task 11/25] Current/Best: 12.24/ 18.06 GFLOPS | Progress: (4/20) | 3.35 s
+[Task 11/25] Current/Best: 15.14/ 18.06 GFLOPS | Progress: (8/20) | 6.14 s
+[Task 11/25] Current/Best: 18.06/ 18.06 GFLOPS | Progress: (12/20) | 8.16 s
+[Task 11/25] Current/Best: 13.42/ 21.09 GFLOPS | Progress: (16/20) | 10.95 s
+[Task 11/25] Current/Best: 19.41/ 21.58 GFLOPS | Progress: (20/20) | 12.98 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.82/ 18.09 GFLOPS | Progress: (4/20) | 5.40 s
-[Task 12/25] Current/Best: 5.21/ 18.09 GFLOPS | Progress: (8/20) | 9.10 s
-[Task 12/25] Current/Best: 19.28/ 19.28 GFLOPS | Progress: (12/20) | 11.10 s
-[Task 12/25] Current/Best: 13.55/ 19.28 GFLOPS | Progress: (16/20) | 13.90 s
-[Task 12/25] Current/Best: 15.12/ 19.28 GFLOPS | Progress: (20/20) | 15.86 s Done.
+[Task 12/25] Current/Best: 7.71/ 18.23 GFLOPS | Progress: (4/20) | 5.34 s
+[Task 12/25] Current/Best: 5.30/ 18.23 GFLOPS | Progress: (8/20) | 9.05 s
+[Task 12/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (12/20) | 11.03 s
+[Task 12/25] Current/Best: 14.38/ 18.93 GFLOPS | Progress: (16/20) | 13.82 s
+[Task 12/25] Current/Best: 15.08/ 19.26 GFLOPS | Progress: (20/20) | 15.74 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.78/ 17.20 GFLOPS | Progress: (4/20) | 3.63 s
-[Task 13/25] Current/Best: 16.03/ 20.88 GFLOPS | Progress: (8/20) | 6.06 s
-[Task 13/25] Current/Best: 19.45/ 21.63 GFLOPS | Progress: (12/20) | 8.95 s
-[Task 13/25] Current/Best: 12.22/ 21.63 GFLOPS | Progress: (16/20) | 12.37 s
-[Task 13/25] Current/Best: 18.80/ 21.63 GFLOPS | Progress: (20/20) | 14.64 s Done.
+[Task 13/25] Current/Best: 9.02/ 17.38 GFLOPS | Progress: (4/20) | 3.64 s
+[Task 13/25] Current/Best: 16.04/ 20.88 GFLOPS | Progress: (8/20) | 6.07 s
+[Task 13/25] Current/Best: 19.44/ 21.51 GFLOPS | Progress: (12/20) | 8.94 s
+[Task 13/25] Current/Best: 12.23/ 21.51 GFLOPS | Progress: (16/20) | 12.37 s
+[Task 13/25] Current/Best: 18.54/ 21.51 GFLOPS | Progress: (20/20) | 14.61 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.30 s
-[Task 14/25] Current/Best: 6.09/ 13.57 GFLOPS | Progress: (8/20) | 5.45 s
-[Task 14/25] Current/Best: 20.64/ 20.64 GFLOPS | Progress: (12/20) | 7.98 s
-[Task 14/25] Current/Best: 16.90/ 20.64 GFLOPS | Progress: (16/20) | 9.62 s Done.
+[Task 14/25] Current/Best: 13.51/ 13.51 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 14/25] Current/Best: 6.12/ 13.51 GFLOPS | Progress: (8/20) | 5.50 s
+[Task 14/25] Current/Best: 20.49/ 20.49 GFLOPS | Progress: (12/20) | 8.04 s
+[Task 14/25] Current/Best: 16.66/ 20.49 GFLOPS | Progress: (16/20) | 9.70 s Done.
-[Task 14/25] Current/Best: 17.21/ 20.64 GFLOPS | Progress: (20/20) | 11.36 s
+[Task 14/25] Current/Best: 17.30/ 20.49 GFLOPS | Progress: (20/20) | 11.42 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.09/ 17.57 GFLOPS | Progress: (4/20) | 2.68 s
-[Task 15/25] Current/Best: 14.26/ 17.99 GFLOPS | Progress: (8/20) | 4.02 s
-[Task 15/25] Current/Best: 10.38/ 22.18 GFLOPS | Progress: (12/20) | 6.15 s
-[Task 15/25] Current/Best: 20.28/ 22.18 GFLOPS | Progress: (16/20) | 9.20 s
-[Task 15/25] Current/Best: 9.68/ 22.18 GFLOPS | Progress: (20/20) | 10.23 s
+[Task 15/25] Current/Best: 16.20/ 17.57 GFLOPS | Progress: (4/20) | 2.65 s
+[Task 15/25] Current/Best: 14.36/ 18.00 GFLOPS | Progress: (8/20) | 3.95 s
+[Task 15/25] Current/Best: 10.38/ 22.29 GFLOPS | Progress: (12/20) | 5.99 s
+[Task 15/25] Current/Best: 20.23/ 22.29 GFLOPS | Progress: (16/20) | 8.93 s
+[Task 15/25] Current/Best: 9.59/ 22.29 GFLOPS | Progress: (20/20) | 9.95 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 19.57/ 19.57 GFLOPS | Progress: (4/20) | 2.97 s
-[Task 16/25] Current/Best: 3.02/ 19.57 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 16/25] Current/Best: 19.58/ 19.58 GFLOPS | Progress: (12/20) | 5.80 s
-[Task 16/25] Current/Best: 17.50/ 19.58 GFLOPS | Progress: (16/20) | 7.16 s
-[Task 16/25] Current/Best: 9.95/ 22.22 GFLOPS | Progress: (20/20) | 9.21 s Done.
+[Task 16/25] Current/Best: 20.35/ 20.35 GFLOPS | Progress: (4/20) | 2.95 s
+[Task 16/25] Current/Best: 3.04/ 20.35 GFLOPS | Progress: (8/20) | 4.58 s
+[Task 16/25] Current/Best: 19.08/ 20.35 GFLOPS | Progress: (12/20) | 5.80 s
+[Task 16/25] Current/Best: 17.78/ 20.35 GFLOPS | Progress: (16/20) | 7.15 s
+[Task 16/25] Current/Best: 10.08/ 22.00 GFLOPS | Progress: (20/20) | 9.21 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.16/ 18.81 GFLOPS | Progress: (4/20) | 4.66 s
-[Task 17/25] Current/Best: 14.36/ 23.01 GFLOPS | Progress: (8/20) | 7.53 s
-[Task 17/25] Current/Best: 16.76/ 23.01 GFLOPS | Progress: (12/20) | 9.60 s
-[Task 17/25] Current/Best: 17.13/ 23.01 GFLOPS | Progress: (16/20) | 11.74 s
-[Task 17/25] Current/Best: 10.02/ 23.01 GFLOPS | Progress: (20/20) | 13.86 s Done.
+[Task 17/25] Current/Best: 13.62/ 18.89 GFLOPS | Progress: (4/20) | 4.70 s
+[Task 17/25] Current/Best: 14.51/ 23.16 GFLOPS | Progress: (8/20) | 7.58 s
+[Task 17/25] Current/Best: 16.80/ 23.16 GFLOPS | Progress: (12/20) | 9.61 s
+[Task 17/25] Current/Best: 16.54/ 23.16 GFLOPS | Progress: (16/20) | 11.74 s
+[Task 17/25] Current/Best: 9.75/ 23.16 GFLOPS | Progress: (20/20) | 13.89 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.10/ 17.83 GFLOPS | Progress: (4/20) | 3.67 s
-[Task 18/25] Current/Best: 10.53/ 19.89 GFLOPS | Progress: (8/20) | 7.13 s
-[Task 18/25] Current/Best: 19.03/ 19.89 GFLOPS | Progress: (12/20) | 9.05 s
-[Task 18/25] Current/Best: 9.91/ 19.89 GFLOPS | Progress: (16/20) | 12.62 s
-[Task 18/25] Current/Best: 20.23/ 20.23 GFLOPS | Progress: (20/20) | 14.15 s Done.
+[Task 18/25] Current/Best: 11.59/ 17.71 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 18/25] Current/Best: 10.64/ 19.66 GFLOPS | Progress: (8/20) | 7.11 s
+[Task 18/25] Current/Best: 19.30/ 19.66 GFLOPS | Progress: (12/20) | 9.03 s
+[Task 18/25] Current/Best: 9.84/ 19.66 GFLOPS | Progress: (16/20) | 12.62 s
+[Task 18/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (20/20) | 14.16 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.04/ 20.22 GFLOPS | Progress: (4/20) | 6.06 s
-[Task 19/25] Current/Best: 2.59/ 20.22 GFLOPS | Progress: (8/20) | 9.32 s
-[Task 19/25] Current/Best: 19.50/ 20.72 GFLOPS | Progress: (12/20) | 12.19 s
-[Task 19/25] Current/Best: 14.01/ 21.36 GFLOPS | Progress: (16/20) | 15.05 s
-[Task 19/25] Current/Best: 2.70/ 23.29 GFLOPS | Progress: (20/20) | 17.81 s Done.
+[Task 19/25] Current/Best: 6.35/ 20.20 GFLOPS | Progress: (4/20) | 6.26 s
+[Task 19/25] Current/Best: 2.60/ 20.20 GFLOPS | Progress: (8/20) | 9.54 s
+[Task 19/25] Current/Best: 18.73/ 20.83 GFLOPS | Progress: (12/20) | 12.31 s
+[Task 19/25] Current/Best: 15.33/ 21.48 GFLOPS | Progress: (16/20) | 15.13 s
+[Task 19/25] Current/Best: 2.70/ 23.20 GFLOPS | Progress: (20/20) | 17.90 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.71/ 15.08 GFLOPS | Progress: (4/20) | 3.31 s Done.
+[Task 20/25] Current/Best: 9.56/ 15.03 GFLOPS | Progress: (4/20) | 3.33 s Done.
Done.
-[Task 20/25] Current/Best: 10.12/ 15.08 GFLOPS | Progress: (8/20) | 6.62 s
-[Task 20/25] Current/Best: 2.33/ 16.68 GFLOPS | Progress: (12/20) | 10.68 s
-[Task 20/25] Current/Best: 12.48/ 16.68 GFLOPS | Progress: (16/20) | 14.29 s
-[Task 20/25] Current/Best: 13.09/ 21.77 GFLOPS | Progress: (20/20) | 16.37 s
+[Task 20/25] Current/Best: 10.36/ 15.03 GFLOPS | Progress: (8/20) | 6.76 s
+[Task 20/25] Current/Best: 2.32/ 16.59 GFLOPS | Progress: (12/20) | 10.67 s
+[Task 20/25] Current/Best: 12.60/ 16.59 GFLOPS | Progress: (16/20) | 14.47 s
+[Task 20/25] Current/Best: 13.45/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.47 GFLOPS | Progress: (4/20) | 3.19 s
-[Task 21/25] Current/Best: 14.27/ 17.47 GFLOPS | Progress: (8/20) | 4.84 s
-[Task 21/25] Current/Best: 1.61/ 17.47 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 21/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (16/20) | 10.44 s
-[Task 21/25] Current/Best: 4.46/ 18.14 GFLOPS | Progress: (20/20) | 17.66 s
+[Task 21/25] Current/Best: 6.38/ 17.56 GFLOPS | Progress: (4/20) | 3.21 s
+[Task 21/25] Current/Best: 14.52/ 17.56 GFLOPS | Progress: (8/20) | 4.77 s
+[Task 21/25] Current/Best: 1.61/ 17.56 GFLOPS | Progress: (12/20) | 6.86 s
+[Task 21/25] Current/Best: 18.28/ 18.28 GFLOPS | Progress: (16/20) | 10.32 s
+[Task 21/25] Current/Best: 4.45/ 18.28 GFLOPS | Progress: (20/20) | 17.59 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 22/25] Current/Best: 2.70/ 17.04 GFLOPS | Progress: (4/20) | 2.67 s
-[Task 22/25] Current/Best: 8.73/ 21.02 GFLOPS | Progress: (8/20) | 4.64 s
-[Task 22/25] Current/Best: 20.09/ 21.02 GFLOPS | Progress: (12/20) | 6.99 s
-[Task 22/25] Current/Best: 14.83/ 21.02 GFLOPS | Progress: (16/20) | 9.06 s
-[Task 22/25] Current/Best: 14.20/ 21.02 GFLOPS | Progress: (20/20) | 10.77 s Done.
+[Task 22/25] Current/Best: 2.70/ 16.94 GFLOPS | Progress: (4/20) | 2.68 s
+[Task 22/25] Current/Best: 9.20/ 21.49 GFLOPS | Progress: (8/20) | 4.58 s
+[Task 22/25] Current/Best: 19.91/ 21.49 GFLOPS | Progress: (12/20) | 6.93 s
+[Task 22/25] Current/Best: 15.19/ 21.49 GFLOPS | Progress: (16/20) | 9.00 s
+[Task 22/25] Current/Best: 15.13/ 21.49 GFLOPS | Progress: (20/20) | 10.67 s Done.
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 23/25] Current/Best: 17.41/ 20.24 GFLOPS | Progress: (4/20) | 3.20 s
-[Task 23/25] Current/Best: 14.47/ 20.24 GFLOPS | Progress: (8/20) | 6.54 s
-[Task 23/25] Current/Best: 20.78/ 21.33 GFLOPS | Progress: (12/20) | 8.36 s
-[Task 23/25] Current/Best: 6.34/ 21.33 GFLOPS | Progress: (16/20) | 15.46 s
-[Task 23/25] Current/Best: 7.65/ 21.33 GFLOPS | Progress: (20/20) | 19.67 s Done.
+[Task 23/25] Current/Best: 17.37/ 20.18 GFLOPS | Progress: (4/20) | 3.23 s
+[Task 23/25] Current/Best: 15.80/ 20.18 GFLOPS | Progress: (8/20) | 6.60 s
+[Task 23/25] Current/Best: 20.85/ 21.25 GFLOPS | Progress: (12/20) | 8.42 s
+[Task 23/25] Current/Best: 6.45/ 21.25 GFLOPS | Progress: (16/20) | 15.48 s
+[Task 23/25] Current/Best: 7.67/ 21.25 GFLOPS | Progress: (20/20) | 19.70 s Done.
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 24/25] Current/Best: 8.40/ 8.40 GFLOPS | Progress: (4/20) | 11.78 s
-[Task 24/25] Current/Best: 1.96/ 8.40 GFLOPS | Progress: (8/20) | 22.81 s
-[Task 24/25] Current/Best: 4.47/ 8.40 GFLOPS | Progress: (12/20) | 34.35 s Done.
+[Task 24/25] Current/Best: 8.50/ 8.50 GFLOPS | Progress: (4/20) | 11.73 s
+[Task 24/25] Current/Best: 1.97/ 8.50 GFLOPS | Progress: (8/20) | 22.76 s
+[Task 24/25] Current/Best: 4.61/ 8.50 GFLOPS | Progress: (12/20) | 34.29 s Done.
Done.
-[Task 24/25] Current/Best: 7.05/ 8.92 GFLOPS | Progress: (16/20) | 39.93 s
-[Task 24/25] Current/Best: 3.37/ 8.92 GFLOPS | Progress: (20/20) | 45.89 s Done.
+[Task 24/25] Current/Best: 7.17/ 8.85 GFLOPS | Progress: (16/20) | 39.79 s
+[Task 24/25] Current/Best: 3.24/ 8.88 GFLOPS | Progress: (20/20) | 45.68 s Done.
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 25/25] Current/Best: 1.54/ 2.90 GFLOPS | Progress: (4/20) | 11.57 s
-[Task 25/25] Current/Best: 5.67/ 7.70 GFLOPS | Progress: (8/20) | 22.78 s
-[Task 25/25] Current/Best: 6.05/ 7.70 GFLOPS | Progress: (12/20) | 34.18 s
-[Task 25/25] Current/Best: 5.82/ 9.20 GFLOPS | Progress: (16/20) | 35.89 s
-[Task 25/25] Current/Best: 2.92/ 9.20 GFLOPS | Progress: (20/20) | 46.58 s
+[Task 25/25] Current/Best: 1.55/ 2.92 GFLOPS | Progress: (4/20) | 11.59 s
+[Task 25/25] Current/Best: 5.87/ 8.01 GFLOPS | Progress: (8/20) | 22.83 s
+[Task 25/25] Current/Best: 5.93/ 8.01 GFLOPS | Progress: (12/20) | 34.24 s
+[Task 25/25] Current/Best: 5.86/ 9.48 GFLOPS | Progress: (16/20) | 35.98 s
+[Task 25/25] Current/Best: 2.89/ 9.48 GFLOPS | Progress: (20/20) | 46.69 s
</pre></div>
</div>
<p>The output from this tuning process will look something like this:</p>
@@ -915,7 +915,7 @@ model using optimized operators to speed up our computations.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"class='</span><span class="si">%s</span><span class="s2">' with probability=</span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#list" title="builtins.list" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">labels</span></a [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621105
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>class='n02123045 tabby, tabby cat' with probability=0.621104
class='n02123159 tiger cat' with probability=0.356378
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
@@ -953,8 +953,8 @@ improvement in comparing the optimized model to the unoptimized model.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"unoptimized: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">))</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 417.4679863499978, 'median': 418.44872064999663, 'std': 2.3841485033104615}
-unoptimized: {'mean': 497.4624736399983, 'median': 497.29978324999706, 'std': 1.4899553090543256}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>optimized: {'mean': 414.44940566000696, 'median': 414.5539063999877, 'std': 0.6336221096039909}
+unoptimized: {'mean': 500.9948443700159, 'median': 501.13534275001257, 'std': 0.7143444638204062}
</pre></div>
</div>
</div>
@@ -968,7 +968,7 @@ models.</p>
<p>Here we presented a simple example using ResNet-50 v2 locally. However, TVM
supports many more features including cross-compilation, remote execution and
profiling/benchmarking.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 17.706 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 10 minutes 18.620 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-autotvm-relay-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/57a45d9bef1af358191e7d50043e652c/autotvm_relay_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">autotvm_relay_x86.py</span></code></a></p>
diff --git a/docs/tutorial/cross_compilation_and_rpc.html b/docs/tutorial/cross_compilation_and_rpc.html
index bba1868ad..a5eafc77f 100644
--- a/docs/tutorial/cross_compilation_and_rpc.html
+++ b/docs/tutorial/cross_compilation_and_rpc.html
@@ -499,7 +499,7 @@ device and returns the measured cost. Network overhead is excluded.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%g</span><span class="s2"> secs/op"</span> <span class="o">%</span> <span class="n">cost</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.298e-07 secs/op
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>1.266e-07 secs/op
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/intro_topi.html b/docs/tutorial/intro_topi.html
index 027c139a1..b24563d6c 100644
--- a/docs/tutorial/intro_topi.html
+++ b/docs/tutorial/intro_topi.html
@@ -459,7 +459,7 @@ we can schedule the following series of operations ending with <code class="code
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sg</span><span class="o">.</span><span class="n">stages</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0xcf5c200)), stage(b, placeholder(b, 0x232fd140)), 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=[i [...]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[stage(a, placeholder(a, 0x20b649f0)), stage(b, placeholder(b, 0x1a63ed80)), 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=[ [...]
</pre></div>
</div>
<p>We can test the correctness by comparing with <code class="code docutils literal notranslate"><span class="pre">numpy</span></code> result as follows</p>
diff --git a/docs/tutorial/sg_execution_times.html b/docs/tutorial/sg_execution_times.html
index a2c517bfa..ca4714890 100644
--- a/docs/tutorial/sg_execution_times.html
+++ b/docs/tutorial/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-tutorial-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>13:10.433</strong> total execution time for <strong>tutorial</strong> files:</p>
+<p><strong>13:20.293</strong> total execution time for <strong>tutorial</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_relay_x86.html#sphx-glr-tutorial-autotvm-relay-x86-py"><span class="std std-ref">Compiling and Optimizing a Model with the Python Interface (AutoTVM)</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_relay_x86.py</span></code>)</p></td>
-<td><p>10:17.706</p></td>
+<td><p>10:18.620</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
-<td><p>01:00.476</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
+<td><p>01:06.970</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="auto_scheduler_matmul_x86.html#sphx-glr-tutorial-auto-scheduler-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Auto-scheduling</span></a> (<code class="docutils literal notranslate"><span class="pre">auto_scheduler_matmul_x86.py</span></code>)</p></td>
-<td><p>00:58.211</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tensor_expr_get_started.html#sphx-glr-tutorial-tensor-expr-get-started-py"><span class="std std-ref">Working with Operators Using Tensor Expression</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_expr_get_started.py</span></code>)</p></td>
+<td><p>00:59.989</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="relay_quick_start.html#sphx-glr-tutorial-relay-quick-start-py"><span class="std std-ref">Quick Start Tutorial for Compiling Deep Learning Models</span></a> (<code class="docutils literal notranslate"><span class="pre">relay_quick_start.py</span></code>)</p></td>
-<td><p>00:28.416</p></td>
+<td><p>00:28.353</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="autotvm_matmul_x86.html#sphx-glr-tutorial-autotvm-matmul-x86-py"><span class="std std-ref">Optimizing Operators with Schedule Templates and AutoTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">autotvm_matmul_x86.py</span></code>)</p></td>
-<td><p>00:23.544</p></td>
+<td><p>00:24.756</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensor_ir_blitz_course.html#sphx-glr-tutorial-tensor-ir-blitz-course-py"><span class="std std-ref">Blitz Course to TensorIR</span></a> (<code class="docutils literal notranslate"><span class="pre">tensor_ir_blitz_course.py</span></code>)</p></td>
-<td><p>00:01.253</p></td>
+<td><p>00:00.757</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="intro_topi.html#sphx-glr-tutorial-intro-topi-py"><span class="std std-ref">Introduction to TOPI</span></a> (<code class="docutils literal notranslate"><span class="pre">intro_topi.py</span></code>)</p></td>
@@ -340,18 +340,18 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="cross_compilation_and_rpc.html#sphx-glr-tutorial-cross-compilation-and-rpc-py"><span class="std std-ref">Cross Compilation and RPC</span></a> (<code class="docutils literal notranslate"><span class="pre">cross_compilation_and_rpc.py</span></code>)</p></td>
-<td><p>00:00.151</p></td>
+<td><p>00:00.172</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="introduction.html#sphx-glr-tutorial-introduction-py"><span class="std std-ref">Introduction</span></a> (<code class="docutils literal notranslate"><span class="pre">introduction.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
+<tr class="row-even"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_command_line_driver.html#sphx-glr-tutorial-tvmc-command-line-driver-py"><span class="std std-ref">Compiling and Optimizing a Model with TVMC</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_command_line_driver.py</span></code>)</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="tvmc_python.html#sphx-glr-tutorial-tvmc-python-py"><span class="std std-ref">Getting Starting using TVMC Python: a high-level API for TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">tvmc_python.py</span></code>)</p></td>
<td><p>00:00.000</p></td>
<td><p>0.0 MB</p></td>
</tr>
diff --git a/docs/tutorial/tensor_expr_get_started.html b/docs/tutorial/tensor_expr_get_started.html
index 19e15e841..9f70ca9fb 100644
--- a/docs/tutorial/tensor_expr_get_started.html
+++ b/docs/tutorial/tensor_expr_get_started.html
@@ -514,8 +514,8 @@ helper function to run a profile of the TVM generated code.</p>
<span class="n">evaluate_addition</span><span class="p">(</span><span class="n">fadd</span><span class="p">,</span> <a href="../reference/api/python/target.html#tvm.target.Target" title="tvm.target.Target" class="sphx-glr-backref-module-tvm-target sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">tgt</span></a><span class="p">,</span> <span class="s2">"naive"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#list" ti [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000009
-naive: 0.000006
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.000008
+naive: 0.000008
</pre></div>
</div>
</div>
@@ -640,10 +640,10 @@ vector: 0.000025
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Operator Timing Performance
- numpy 8.542999999008317e-06 1.0
- naive 5.9193e-06 0.692883062236582
-parallel 6.9181e-06 0.8097974951191692
- vector 2.4738799999999998e-05 2.8957977294711124
+ numpy 7.755080005154014e-06 1.0
+ naive 8.0261e-06 1.0349474144258817
+parallel 6.9596e-06 0.8974246552420685
+ vector 2.47975e-05 3.1975814541590313
</pre></div>
</div>
<div class="admonition-code-specialization admonition">
@@ -959,7 +959,7 @@ matrix multiplication.</p>
<span class="n">answer</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">dot</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">numpy</span><span class="p">(),</span> <span class="n">b</span><span class="o">.</span><span class="n">numpy</span><span class="p">())</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019346
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019455
</pre></div>
</div>
<p>Now we write a basic matrix multiplication using TVM TE and verify that it
@@ -1002,7 +1002,7 @@ optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-none: 3.350288
+none: 3.313207
</pre></div>
</div>
<p>Let’s take a look at the intermediate representation of the operator and
@@ -1069,7 +1069,7 @@ schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-blocking: 0.307988
+blocking: 0.316026
</pre></div>
</div>
<p>By reordering the computation to take advantage of caching, you should see a
@@ -1130,7 +1130,7 @@ already cache friendly from our previous optimizations.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-vectorization: 0.349094
+vectorization: 0.346220
@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], []),
@@ -1187,7 +1187,7 @@ more cache friendly.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-loop permutation: 0.119802
+loop permutation: 0.119249
@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], []),
@@ -1265,7 +1265,7 @@ optimized schedule.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-array packing: 0.110999
+array packing: 0.110582
@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], []),
@@ -1341,7 +1341,7 @@ to `C</cite> when all the block results are ready.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-block caching: 0.111005
+block caching: 0.111336
@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], []),
@@ -1410,7 +1410,7 @@ of thread-level parallelization.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-parallelization: 0.145153
+parallelization: 0.144375
@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], []),
@@ -1472,13 +1472,13 @@ working, we can compare the results.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span> Operator Timing Performance
- none 3.3502878743 1.0
- blocking 0.3079883106 0.09192890944165513
- vectorization 0.3490941228 0.10419824680675799
-loop permutation 0.1198024985 0.03575886699737144
- array packing 0.1109986171 0.03313106851249066
- block caching 0.11100475349999998 0.03313290011629016
- parallelization 0.14515298299999999 0.04332552558049294
+ none 3.3132068332 1.0
+ blocking 0.3160257106 0.09538363480156545
+ vectorization 0.3462197748 0.10449687937701431
+loop permutation 0.11924868389999999 0.03599192260050539
+ array packing 0.1105820952 0.0333761520989006
+ block caching 0.11133638770000001 0.0336038144628803
+ parallelization 0.1443750433 0.043575620408991496
</pre></div>
</div>
<p>Note that the outputs on the web page reflect the running times on a
@@ -1510,7 +1510,6 @@ is</p>
you can build generic templates of the matrix multiplication and other
operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.476 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-tensor-expr-get-started-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/40a01cffb015a67aaec0fad7e27cf80d/tensor_expr_get_started.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">tensor_expr_get_started.py</span></code></a></p>