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 2022/06/10 02:20:32 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@fe299d76882aa030851126cfbf32bf272492dc43)
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 3177b6234 deploying docs (apache/tvm@fe299d76882aa030851126cfbf32bf272492dc43)
3177b6234 is described below
commit 3177b62342360a9024b95df7047e5bd8f431e234
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 10 02:20:26 2022 +0000
deploying docs (apache/tvm@fe299d76882aa030851126cfbf32bf272492dc43)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 7 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 5 +
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 10 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 16 +-
.../tune_conv2d_layer_cuda.rst.txt | 1306 ++-----------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 78 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 12 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 2 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 2035 +++++++++++++++++++-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 6 +-
docs/how_to/compile_models/from_tensorflow.html | 1 +
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 58 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 36 +-
docs/how_to/deploy_models/sg_execution_times.html | 18 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 10 +-
docs/how_to/extend_tvm/use_pass_instrument.html | 16 +-
docs/how_to/optimize_operators/opt_conv_cuda.html | 2 +-
.../optimize_operators/opt_conv_tensorcore.html | 2 +-
docs/how_to/optimize_operators/opt_gemm.html | 16 +-
.../optimize_operators/sg_execution_times.html | 8 +-
.../sg_execution_times.html | 14 +-
.../tune_conv2d_layer_cuda.html | 1306 ++-----------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 78 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 12 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 2 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 45 +-
117 files changed, 3125 insertions(+), 3293 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 f8e157007..0b9aa2bfe 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -98,7 +98,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc559b520-d477-470f-a22c-4398d7b782e2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6e7a2414-dad0-494e-b934-94211cb4012d 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 e6beae4be..fda5bc9ad 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -100,7 +100,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:42, 94.0kB/s]
0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
0%| | 72.0k/41.5M [00:00<04:59, 145kB/s]
0%| | 136k/41.5M [00:00<03:04, 235kB/s]
1%| | 272k/41.5M [00:00<01:38, 437kB/s]
1%|1 | 552k/41.5M [00:01<00:50, 845kB/s]
3%|2 | 1.09M/41.5M [00:01<00:25, 1.64MB/s]
4%|3 | 1.65M/41.5M [00:01<00:19, 2.19MB/s]
5%|5 | 2.22M/41.5M [00:01<00:16, 2.57MB/s]
7%|6 | 2.80M/41.5M [00:01<00:14, 2.84MB/s]
8%|8 | 3.40M/41.5M [00:01<00:12, 3.07MB/s]
10%|9 | 4.02M/41.5M [00:02<00:11, 3.28MB/s]
11%|#1 | 4.69M/41.5M [00:02<00:11, 3.49MB/s]
13%|#2 | 5.38M/41.5M [00:02<00:10, 3.69MB/s]
15%|#4 | 6.11M/41.5M [00:02<00:09, 3.89MB/s]
17%|#6 | 6.88M/41.5M [00:02<00:08, 4.10MB/s]
18%|#8 | 7.67M/41.5M [00:02<00
:08, 4.30MB/s]
21%|## | 8.52M/41.5M [00:03<00:07, 4.52MB/s]
23%|##2 | 9.40M/41.5M [00:03<00:07, 4.75MB/s]
25%|##4 | 10.3M/41.5M [00:03<00:06, 4.99MB/s]
27%|##7 | 11.3M/41.5M [00:03<00:06, 5.25MB/s]
30%|##9 | 12.3M/41.5M [00:03<00:05, 5.51MB/s]
32%|###2 | 13.4M/41.5M [00:04<00:05, 5.79MB/s]
35%|###5 | 14.5M/41.5M [00:04<00:04, 6.07MB/s]
38%|###7 | 15.7M/41.5M [00:04<00:04, 6.38MB/s]
41%|#### | 17.0M/41.5M [00:04<00:03, 6.69MB/s]
44%|####4 | 18.3M/41.5M [00:04<00:03, 7.03MB/s]
47%|####7 | 19.6M/41.5M [00:04<00:03, 7.37MB/s]
51%|##### | 21.1M/41.5M [00:05<00:02, 7.74MB/s]
54%|#####4 | 22.6M/41.5M [00:05<00:02, 8.08MB/s]
58%|#####7 | 24.0M/41.5M [00:05<00:02, 8.32MB/s]
61%|######1 | 25.5M/41.5M [00:05<00:01, 8.48MB/s]
65%|######5 | 27.0M/41.5M [00:05<00:01, 8.59MB/s]
69%|######8 | 28.5M/41.5M [00:05<00:01, 8.64MB/s]
72%|####
###2 | 29.9M/41.5M [00:06<00:01, 8.71MB/s]
76%|#######5 | 31.4M/41.5M [00:06<00:01, 8.76MB/s]
79%|#######9 | 32.9M/41.5M [00:06<00:01, 8.78MB/s]
83%|########2 | 34.4M/41.5M [00:06<00:00, 8.81MB/s]
86%|########6 | 35.9M/41.5M [00:06<00:00, 8.83MB/s]
90%|######### | 37.4M/41.5M [00:07<00:00, 8.84MB/s]
94%|#########3| 38.8M/41.5M [00:07<00:00, 8.85MB/s]
97%|#########7| 40.3M/41.5M [00:07<00:00, 8.84MB/s]
100%|##########| 41.5M/41.5M [00:07<00:00, 5.90MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 8.00k/41.5M [00:00<41:10, 17.6kB/s]
0%| | 56.0k/41.5M [00:00<07:30, 96.3kB/s]
0%| | 72.0k/41.5M [00:00<07:36, 95.1kB/s]
0%| | 88.0k/41.5M [00:01<07:40, 94.2kB/s]
0%| | 104k/41.5M [00:01<07:43, 93.6kB/s]
0%| | 120k/41.5M [00:01<07:45, 93.2kB/s]
0%| | 136k/41.5M [00:01<10:07, 71.4kB/s]
0%| | 160k/41.5M [00:01<08:12, 88.0kB/s]
0%| | 176k/41.5M [00:02<10:13, 70.6kB/s]
0%| | 200k/41.5M [00:02<12:12, 59.1kB/s]
1%| | 232k/41.5M [00:03<08:47, 82.1kB/s]
1%| | 248k/41.5M [00:03<10:20, 69.7kB/s]
1%| | 264k/41.5M [00:03<09:43, 74.2kB/s]
1%| | 280k/41.5M [00:03<09:13, 78.1kB/s]
1%| | 296k/41.5M [00:03<08:50, 81.5kB/s]
1%| | 312k/41.5M [00:04<08:32, 84.2kB/s]
1%| | 328k/41.5M [00:04<10:33, 6
8.2kB/s]
1%| | 344k/41.5M [00:04<09:45, 73.7kB/s]
1%| | 360k/41.5M [00:04<11:27, 62.8kB/s]
1%| | 384k/41.5M [00:05<09:02, 79.5kB/s]
1%| | 400k/41.5M [00:05<08:42, 82.5kB/s]
1%| | 416k/41.5M [00:05<08:26, 85.0kB/s]
1%|1 | 432k/41.5M [00:05<10:27, 68.6kB/s]
1%|1 | 448k/41.5M [00:06<09:41, 74.1kB/s]
1%|1 | 464k/41.5M [00:06<09:07, 78.6kB/s]
1%|1 | 480k/41.5M [00:06<08:43, 82.2kB/s]
1%|1 | 496k/41.5M [00:06<10:44, 66.7kB/s]
1%|1 | 520k/41.5M [00:06<08:34, 83.5kB/s]
1%|1 | 536k/41.5M [00:07<08:21, 85.7kB/s]
1%|1 | 552k/41.5M [00:07<10:20, 69.2kB/s]
1%|1 | 568k/41.5M [00:07<09:36, 74.5kB/s]
1%|1 | 584k/41.5M [00:07<09:03, 78.9kB/s]
1%|1 | 600k/41.5M [00:07<08:40, 82.4kB/s]
1%|1 | 616k/41.5M [00:08<08:24, 85.1kB/s]
1%|1 | 632k/41.5M [00:
08<10:29, 68.0kB/s]
2%|1 | 648k/41.5M [00:08<09:40, 73.8kB/s]
2%|1 | 656k/41.5M [00:08<10:41, 66.8kB/s]
2%|1 | 672k/41.5M [00:09<09:42, 73.6kB/s]
2%|1 | 688k/41.5M [00:09<09:03, 78.7kB/s]
2%|1 | 696k/41.5M [00:09<10:15, 69.5kB/s]
2%|1 | 712k/41.5M [00:09<12:04, 59.1kB/s]
2%|1 | 736k/41.5M [00:09<09:06, 78.2kB/s]
2%|1 | 752k/41.5M [00:10<09:14, 77.1kB/s]
2%|1 | 768k/41.5M [00:10<10:30, 67.8kB/s]
2%|1 | 784k/41.5M [00:10<09:40, 73.5kB/s]
2%|1 | 792k/41.5M [00:10<10:40, 66.6kB/s]
2%|1 | 808k/41.5M [00:11<09:41, 73.4kB/s]
2%|1 | 816k/41.5M [00:11<10:47, 65.9kB/s]
2%|1 | 832k/41.5M [00:11<09:41, 73.3kB/s]
2%|1 | 848k/41.5M [00:11<09:01, 78.8kB/s]
2%|2 | 864k/41.5M [00:11<09:09, 77.6kB/s]
2%|2 | 872k/41.5M [00:11<09:40, 73.4kB/s]
2%|2 | 888k
/41.5M [00:12<08:58, 79.1kB/s]
2%|2 | 904k/41.5M [00:12<08:32, 83.0kB/s]
2%|2 | 920k/41.5M [00:12<08:16, 85.8kB/s]
2%|2 | 936k/41.5M [00:12<08:37, 82.1kB/s]
2%|2 | 952k/41.5M [00:12<08:57, 79.2kB/s]
2%|2 | 968k/41.5M [00:13<08:33, 82.8kB/s]
2%|2 | 984k/41.5M [00:13<08:55, 79.4kB/s]
2%|2 | 992k/41.5M [00:13<09:19, 75.9kB/s]
2%|2 | 0.98M/41.5M [00:13<08:45, 80.8kB/s]
2%|2 | 1.00M/41.5M [00:13<08:24, 84.2kB/s]
2%|2 | 1.02M/41.5M [00:13<08:10, 86.6kB/s]
2%|2 | 1.03M/41.5M [00:14<08:00, 88.3kB/s]
3%|2 | 1.05M/41.5M [00:14<07:53, 89.5kB/s]
3%|2 | 1.06M/41.5M [00:14<07:49, 90.3kB/s]
3%|2 | 1.08M/41.5M [00:14<07:46, 90.9kB/s]
3%|2 | 1.09M/41.5M [00:15<10:40, 66.1kB/s]
3%|2 | 1.12M/41.5M [00:15<07:29, 94.1kB/s]
3%|2 | 1.14M/41.5M [00:15<07:58, 88.5kB/s]
3%|2 | 1.16M/41.5M [00:15<09:25, 74.8kB/s]
3%|2 | 1.17M/41.5M [00:15<08:55, 78.9kB/s]
3%|2 | 1.19M/41.5M [00:16<08:33, 82.2kB/s]
3%|2 | 1.20M/41.5M [00:16<08:47, 80.0kB/s]
3%|2 | 1.22M/41.5M [00:16<08:27, 83.2kB/s]
3%|2 | 1.23M/41.5M [00:16<09:55, 70.9kB/s]
3%|3 | 1.25M/41.5M [00:17<09:14, 76.1kB/s]
3%|3 | 1.27M/41.5M [00:17<08:45, 80.2kB/s]
3%|3 | 1.28M/41.5M [00:17<08:25, 83.5kB/s]
3%|3 | 1.30M/41.5M [00:17<08:10, 85.9kB/s]
3%|3 | 1.31M/41.5M [00:17<08:00, 87.7kB/s]
3%|3 | 1.33M/41.5M [00:17<07:53, 89.0kB/s]
3%|3 | 1.34M/41.5M [00:18<07:47, 90.0kB/s]
3%|3 | 1.36M/41.5M [00:18<07:44, 90.7kB/s]
3%|3 | 1.38M/41.5M [00:18<06:41, 105kB/s]
3%|3 | 1.40M/41.5M [00:18<06:56, 101kB/s]
3%|3 | 1.41M/41.5M [00:18<07:07, 98.4kB/s]
3%|3 | 1.43M/41.5M
[00:18<07:15, 96.6kB/s]
3%|3 | 1.45M/41.5M [00:19<07:20, 95.3kB/s]
4%|3 | 1.46M/41.5M [00:19<07:24, 94.4kB/s]
4%|3 | 1.48M/41.5M [00:19<07:27, 93.7kB/s]
4%|3 | 1.50M/41.5M [00:19<06:31, 107kB/s]
4%|3 | 1.52M/41.5M [00:19<06:48, 103kB/s]
4%|3 | 1.53M/41.5M [00:20<07:00, 99.6kB/s]
4%|3 | 1.55M/41.5M [00:20<07:40, 90.9kB/s]
4%|3 | 1.57M/41.5M [00:20<06:14, 112kB/s]
4%|3 | 1.59M/41.5M [00:20<06:35, 106kB/s]
4%|3 | 1.60M/41.5M [00:20<06:51, 102kB/s]
4%|3 | 1.62M/41.5M [00:20<07:02, 98.9kB/s]
4%|3 | 1.63M/41.5M [00:21<07:11, 96.9kB/s]
4%|3 | 1.65M/41.5M [00:21<07:17, 95.5kB/s]
4%|4 | 1.67M/41.5M [00:21<06:25, 108kB/s]
4%|4 | 1.69M/41.5M [00:21<06:42, 104kB/s]
4%|4 | 1.71M/41.5M [00:21<06:06, 114kB/s]
4%|4 | 1.73M/41.5M [00:21<06:28, 107kB/s]
4%|4
| 1.75M/41.5M [00:22<05:56, 117kB/s]
4%|4 | 1.77M/41.5M [00:22<05:38, 123kB/s]
4%|4 | 1.80M/41.5M [00:22<05:25, 128kB/s]
4%|4 | 1.81M/41.5M [00:22<05:55, 117kB/s]
4%|4 | 1.84M/41.5M [00:22<05:36, 124kB/s]
4%|4 | 1.85M/41.5M [00:23<06:30, 106kB/s]
5%|4 | 1.88M/41.5M [00:23<05:35, 124kB/s]
5%|4 | 1.89M/41.5M [00:23<06:03, 114kB/s]
5%|4 | 1.91M/41.5M [00:23<06:25, 108kB/s]
5%|4 | 1.93M/41.5M [00:23<05:54, 117kB/s]
5%|4 | 1.95M/41.5M [00:23<06:18, 109kB/s]
5%|4 | 1.97M/41.5M [00:24<05:50, 118kB/s]
5%|4 | 1.99M/41.5M [00:24<05:33, 124kB/s]
5%|4 | 2.01M/41.5M [00:24<06:01, 115kB/s]
5%|4 | 2.02M/41.5M [00:24<07:17, 94.7kB/s]
5%|4 | 2.05M/41.5M [00:24<05:46, 119kB/s]
5%|4 | 2.07M/41.5M [00:25<06:10, 112kB/s]
5%|5 | 2.09M/41.5M [00:25<05:46, 119kB/
s]
5%|5 | 2.11M/41.5M [00:25<06:10, 112kB/s]
5%|5 | 2.13M/41.5M [00:25<05:45, 119kB/s]
5%|5 | 2.15M/41.5M [00:25<06:10, 111kB/s]
5%|5 | 2.17M/41.5M [00:25<05:45, 119kB/s]
5%|5 | 2.20M/41.5M [00:26<05:29, 125kB/s]
5%|5 | 2.22M/41.5M [00:26<05:19, 129kB/s]
5%|5 | 2.24M/41.5M [00:26<05:12, 132kB/s]
5%|5 | 2.26M/41.5M [00:26<05:42, 120kB/s]
5%|5 | 2.28M/41.5M [00:26<05:27, 126kB/s]
6%|5 | 2.30M/41.5M [00:27<06:52, 99.5kB/s]
6%|5 | 2.34M/41.5M [00:27<05:11, 132kB/s]
6%|5 | 2.36M/41.5M [00:27<05:37, 122kB/s]
6%|5 | 2.38M/41.5M [00:27<06:00, 114kB/s]
6%|5 | 2.39M/41.5M [00:27<06:20, 108kB/s]
6%|5 | 2.41M/41.5M [00:28<05:51, 116kB/s]
6%|5 | 2.44M/41.5M [00:28<05:33, 123kB/s]
6%|5 | 2.46M/41.5M [00:28<05:21, 127kB/s]
6%|5 | 2.48M/41.5M [00:28<
05:49, 117kB/s]
6%|6 | 2.50M/41.5M [00:28<05:31, 123kB/s]
6%|6 | 2.52M/41.5M [00:28<05:19, 128kB/s]
6%|6 | 2.55M/41.5M [00:29<05:11, 131kB/s]
6%|6 | 2.57M/41.5M [00:29<05:06, 133kB/s]
6%|6 | 2.59M/41.5M [00:29<05:02, 135kB/s]
6%|6 | 2.62M/41.5M [00:29<05:00, 136kB/s]
6%|6 | 2.63M/41.5M [00:29<06:18, 108kB/s]
6%|6 | 2.66M/41.5M [00:30<05:16, 129kB/s]
6%|6 | 2.69M/41.5M [00:30<05:17, 128kB/s]
7%|6 | 2.70M/41.5M [00:30<05:35, 121kB/s]
7%|6 | 2.73M/41.5M [00:30<07:26, 91.0kB/s]
7%|6 | 2.76M/41.5M [00:31<05:34, 122kB/s]
7%|6 | 2.77M/41.5M [00:31<05:56, 114kB/s]
7%|6 | 2.79M/41.5M [00:31<06:15, 108kB/s]
7%|6 | 2.81M/41.5M [00:31<05:56, 114kB/s]
7%|6 | 2.83M/41.5M [00:31<06:16, 108kB/s]
7%|6 | 2.84M/41.5M [00:31<06:22, 106kB/s]
7%|6 | 2.86M/
41.5M [00:32<06:09, 110kB/s]
7%|6 | 2.88M/41.5M [00:32<06:00, 112kB/s]
7%|6 | 2.89M/41.5M [00:32<06:22, 106kB/s]
7%|7 | 2.91M/41.5M [00:32<06:38, 101kB/s]
7%|7 | 2.93M/41.5M [00:32<05:57, 113kB/s]
7%|7 | 2.95M/41.5M [00:32<05:34, 121kB/s]
7%|7 | 2.98M/41.5M [00:33<05:20, 126kB/s]
7%|7 | 3.00M/41.5M [00:33<05:10, 130kB/s]
7%|7 | 3.02M/41.5M [00:33<06:36, 102kB/s]
7%|7 | 3.06M/41.5M [00:33<05:36, 120kB/s]
7%|7 | 3.08M/41.5M [00:34<06:41, 100kB/s]
7%|7 | 3.11M/41.5M [00:34<06:13, 108kB/s]
8%|7 | 3.12M/41.5M [00:34<06:25, 104kB/s]
8%|7 | 3.14M/41.5M [00:34<06:36, 101kB/s]
8%|7 | 3.16M/41.5M [00:34<06:54, 96.9kB/s]
8%|7 | 3.17M/41.5M [00:35<06:51, 97.6kB/s]
8%|7 | 3.19M/41.5M [00:35<08:55, 75.0kB/s]
8%|7 | 3.20M/41.5M [00:35<08:27, 79.1kB/s]
8%|7
| 3.22M/41.5M [00:35<08:06, 82.5kB/s]
8%|7 | 3.23M/41.5M [00:36<08:30, 78.5kB/s]
8%|7 | 3.25M/41.5M [00:36<07:29, 89.2kB/s]
8%|7 | 3.27M/41.5M [00:36<09:32, 70.0kB/s]
8%|7 | 3.28M/41.5M [00:36<08:51, 75.4kB/s]
8%|7 | 3.30M/41.5M [00:36<08:22, 79.7kB/s]
8%|7 | 3.31M/41.5M [00:37<08:01, 83.1kB/s]
8%|8 | 3.33M/41.5M [00:37<07:47, 85.6kB/s]
8%|8 | 3.34M/41.5M [00:37<07:37, 87.5kB/s]
8%|8 | 3.36M/41.5M [00:37<07:29, 88.9kB/s]
8%|8 | 3.38M/41.5M [00:37<07:24, 89.9kB/s]
8%|8 | 3.39M/41.5M [00:37<07:21, 90.6kB/s]
8%|8 | 3.41M/41.5M [00:38<06:22, 104kB/s]
8%|8 | 3.42M/41.5M [00:38<06:03, 110kB/s]
8%|8 | 3.44M/41.5M [00:38<06:24, 104kB/s]
8%|8 | 3.45M/41.5M [00:38<06:37, 100kB/s]
8%|8 | 3.47M/41.5M [00:38<06:47, 97.8kB/s]
8%|8 | 3.48M/41.5M [00:38<06:
15, 106kB/s]
8%|8 | 3.51M/41.5M [00:39<06:15, 106kB/s]
9%|8 | 3.53M/41.5M [00:39<05:43, 116kB/s]
9%|8 | 3.55M/41.5M [00:39<05:24, 123kB/s]
9%|8 | 3.57M/41.5M [00:39<05:18, 125kB/s]
9%|8 | 3.59M/41.5M [00:39<05:07, 129kB/s]
9%|8 | 3.62M/41.5M [00:40<07:04, 93.7kB/s]
9%|8 | 3.66M/41.5M [00:40<04:26, 149kB/s]
9%|8 | 3.69M/41.5M [00:40<04:53, 135kB/s]
9%|8 | 3.71M/41.5M [00:40<04:51, 136kB/s]
9%|8 | 3.73M/41.5M [00:40<04:53, 135kB/s]
9%|9 | 3.74M/41.5M [00:40<05:23, 122kB/s]
9%|9 | 3.77M/41.5M [00:41<06:29, 101kB/s]
9%|9 | 3.79M/41.5M [00:41<06:10, 107kB/s]
9%|9 | 3.83M/41.5M [00:41<06:20, 104kB/s]
9%|9 | 3.87M/41.5M [00:42<04:40, 141kB/s]
9%|9 | 3.89M/41.5M [00:42<07:02, 93.2kB/s]
9%|9 | 3.92M/41.5M [00:42<05:55, 111kB/s]
9%|9 | 3.94M/
41.5M [00:43<07:28, 87.7kB/s]
10%|9 | 3.95M/41.5M [00:43<07:23, 88.7kB/s]
10%|9 | 3.97M/41.5M [00:43<07:19, 89.5kB/s]
10%|9 | 3.98M/41.5M [00:43<07:16, 90.0kB/s]
10%|9 | 4.00M/41.5M [00:44<12:48, 51.1kB/s]
10%|9 | 4.04M/41.5M [00:44<07:59, 81.9kB/s]
10%|9 | 4.05M/41.5M [00:44<08:36, 76.0kB/s]
10%|9 | 4.07M/41.5M [00:44<08:14, 79.3kB/s]
10%|9 | 4.09M/41.5M [00:45<08:47, 74.4kB/s]
10%|9 | 4.10M/41.5M [00:45<08:19, 78.4kB/s]
10%|9 | 4.12M/41.5M [00:45<07:59, 81.8kB/s]
10%|9 | 4.13M/41.5M [00:45<07:43, 84.4kB/s]
10%|9 | 4.15M/41.5M [00:45<07:32, 86.5kB/s]
10%|# | 4.16M/41.5M [00:46<09:27, 69.0kB/s]
10%|# | 4.19M/41.5M [00:46<07:37, 85.4kB/s]
10%|# | 4.20M/41.5M [00:46<09:22, 69.6kB/s]
10%|# | 4.22M/41.5M [00:47<08:43, 74.6kB/s]
10%|# | 4.23M/41.5M [00:47<08:15, 78.9kB/s
]
10%|# | 4.25M/41.5M [00:47<07:54, 82.3kB/s]
10%|# | 4.27M/41.5M [00:47<07:39, 85.0kB/s]
10%|# | 4.28M/41.5M [00:47<07:28, 87.0kB/s]
10%|# | 4.30M/41.5M [00:47<07:20, 88.5kB/s]
10%|# | 4.31M/41.5M [00:48<07:15, 89.5kB/s]
10%|# | 4.33M/41.5M [00:48<07:11, 90.3kB/s]
10%|# | 4.34M/41.5M [00:48<07:08, 90.9kB/s]
11%|# | 4.36M/41.5M [00:48<07:51, 82.5kB/s]
11%|# | 4.38M/41.5M [00:48<06:52, 94.4kB/s]
11%|# | 4.39M/41.5M [00:48<06:55, 93.7kB/s]
11%|# | 4.41M/41.5M [00:49<06:56, 93.3kB/s]
11%|# | 4.42M/41.5M [00:49<06:58, 93.0kB/s]
11%|# | 4.44M/41.5M [00:49<06:58, 92.8kB/s]
11%|# | 4.45M/41.5M [00:49<06:59, 92.6kB/s]
11%|# | 4.47M/41.5M [00:49<08:13, 78.7kB/s]
11%|# | 4.49M/41.5M [00:50<07:15, 89.1kB/s]
11%|# | 4.51M/41.5M [00:50<07:11, 89.9kB/s]
11%|# | 4.52M
/41.5M [00:50<07:30, 86.1kB/s]
11%|# | 4.54M/41.5M [00:50<06:58, 92.6kB/s]
11%|# | 4.55M/41.5M [00:50<06:58, 92.5kB/s]
11%|#1 | 4.57M/41.5M [00:51<06:44, 95.7kB/s]
11%|#1 | 4.59M/41.5M [00:51<06:17, 102kB/s]
11%|#1 | 4.61M/41.5M [00:51<06:19, 102kB/s]
11%|#1 | 4.62M/41.5M [00:51<06:16, 103kB/s]
11%|#1 | 4.64M/41.5M [00:51<05:58, 108kB/s]
11%|#1 | 4.66M/41.5M [00:51<06:07, 105kB/s]
11%|#1 | 4.68M/41.5M [00:52<05:40, 113kB/s]
11%|#1 | 4.70M/41.5M [00:52<05:55, 109kB/s]
11%|#1 | 4.72M/41.5M [00:52<05:31, 116kB/s]
11%|#1 | 4.74M/41.5M [00:52<05:12, 123kB/s]
11%|#1 | 4.77M/41.5M [00:52<05:35, 115kB/s]
12%|#1 | 4.79M/41.5M [00:53<05:16, 121kB/s]
12%|#1 | 4.81M/41.5M [00:53<05:04, 126kB/s]
12%|#1 | 4.84M/41.5M [00:53<04:55, 130kB/s]
12%|#1 | 4.86M/41.5M [00:53<04:18, 149kB/s]
12%|#
1 | 4.88M/41.5M [00:53<04:24, 145kB/s]
12%|#1 | 4.91M/41.5M [00:53<04:11, 153kB/s]
12%|#1 | 4.92M/41.5M [00:53<04:25, 145kB/s]
12%|#1 | 4.94M/41.5M [00:54<04:42, 136kB/s]
12%|#1 | 4.97M/41.5M [00:54<04:11, 152kB/s]
12%|#2 | 4.99M/41.5M [00:54<04:19, 148kB/s]
12%|#2 | 5.02M/41.5M [00:54<04:00, 159kB/s]
12%|#2 | 5.05M/41.5M [00:54<03:41, 173kB/s]
12%|#2 | 5.08M/41.5M [00:54<03:36, 177kB/s]
12%|#2 | 5.11M/41.5M [00:55<03:58, 160kB/s]
12%|#2 | 5.14M/41.5M [00:55<03:23, 187kB/s]
12%|#2 | 5.18M/41.5M [00:55<04:32, 140kB/s]
13%|#2 | 5.22M/41.5M [00:55<04:06, 154kB/s]
13%|#2 | 5.27M/41.5M [00:56<03:15, 194kB/s]
13%|#2 | 5.29M/41.5M [00:56<03:11, 198kB/s]
13%|#2 | 5.31M/41.5M [00:56<03:02, 208kB/s]
13%|#2 | 5.34M/41.5M [00:56<03:25, 185kB/s]
13%|#2 | 5.36M/41.5M [00:56<03:28, 181kB/s]
13%|#2 | 5.38M/41.5M [00:56<05:01, 126kB/s]
13%|#3 | 5.44M/41.5M [00:57<03:13, 196kB/s]
13%|#3 | 5.47M/41.5M [00:57<03:16, 193kB/s]
13%|#3 | 5.49M/41.5M [00:57<03:33, 177kB/s]
13%|#3 | 5.52M/41.5M [00:57<03:48, 165kB/s]
13%|#3 | 5.54M/41.5M [00:57<03:28, 181kB/s]
13%|#3 | 5.56M/41.5M [00:57<03:45, 167kB/s]
13%|#3 | 5.59M/41.5M [00:58<03:38, 172kB/s]
14%|#3 | 5.62M/41.5M [00:58<03:28, 180kB/s]
14%|#3 | 5.64M/41.5M [00:58<03:28, 181kB/s]
14%|#3 | 5.66M/41.5M [00:58<03:46, 166kB/s]
14%|#3 | 5.69M/41.5M [00:58<03:58, 157kB/s]
14%|#3 | 5.71M/41.5M [00:58<03:33, 175kB/s]
14%|#3 | 5.74M/41.5M [00:58<03:29, 179kB/s]
14%|#3 | 5.77M/41.5M [00:59<05:01, 124kB/s]
14%|#4 | 5.82M/41.5M [00:59<03:14, 193kB/s]
14%|#4 | 5.85M/41.5M [00:59<04:57, 126kB/s]
14%|#4 | 5.89M/41.5M [01:00<04:1
1, 148kB/s]
14%|#4 | 5.91M/41.5M [01:00<04:15, 146kB/s]
14%|#4 | 5.94M/41.5M [01:00<04:18, 144kB/s]
14%|#4 | 5.96M/41.5M [01:00<06:39, 93.2kB/s]
14%|#4 | 5.98M/41.5M [01:01<06:22, 97.5kB/s]
14%|#4 | 6.02M/41.5M [01:01<05:04, 122kB/s]
15%|#4 | 6.03M/41.5M [01:01<05:23, 115kB/s]
15%|#4 | 6.05M/41.5M [01:01<05:40, 109kB/s]
15%|#4 | 6.06M/41.5M [01:01<05:55, 105kB/s]
15%|#4 | 6.09M/41.5M [01:02<05:25, 114kB/s]
15%|#4 | 6.10M/41.5M [01:02<05:44, 108kB/s]
15%|#4 | 6.12M/41.5M [01:02<05:17, 117kB/s]
15%|#4 | 6.15M/41.5M [01:02<05:01, 123kB/s]
15%|#4 | 6.17M/41.5M [01:02<04:50, 127kB/s]
15%|#4 | 6.20M/41.5M [01:02<04:43, 131kB/s]
15%|#4 | 6.21M/41.5M [01:03<05:09, 119kB/s]
15%|#5 | 6.23M/41.5M [01:03<05:32, 111kB/s]
15%|#5 | 6.25M/41.5M [01:03<05:09, 119kB/s]
15%|#5 | 6.27M/41.
5M [01:03<05:32, 111kB/s]
15%|#5 | 6.29M/41.5M [01:03<05:09, 119kB/s]
15%|#5 | 6.30M/41.5M [01:03<05:31, 111kB/s]
15%|#5 | 6.33M/41.5M [01:04<06:42, 91.7kB/s]
15%|#5 | 6.36M/41.5M [01:04<05:21, 115kB/s]
15%|#5 | 6.38M/41.5M [01:04<05:38, 109kB/s]
15%|#5 | 6.39M/41.5M [01:04<05:52, 104kB/s]
15%|#5 | 6.41M/41.5M [01:05<07:46, 78.9kB/s]
16%|#5 | 6.45M/41.5M [01:05<05:19, 115kB/s]
16%|#5 | 6.46M/41.5M [01:05<05:36, 109kB/s]
16%|#5 | 6.48M/41.5M [01:05<05:50, 105kB/s]
16%|#5 | 6.49M/41.5M [01:05<06:02, 101kB/s]
16%|#5 | 6.51M/41.5M [01:06<06:11, 98.7kB/s]
16%|#5 | 6.52M/41.5M [01:06<06:18, 96.9kB/s]
16%|#5 | 6.54M/41.5M [01:06<06:23, 95.5kB/s]
16%|#5 | 6.55M/41.5M [01:06<06:27, 94.6kB/s]
16%|#5 | 6.58M/41.5M [01:06<05:40, 108kB/s]
16%|#5 | 6.59M/41.5M [01:07<05:55, 103kB/s]
16%|#
5 | 6.61M/41.5M [01:07<05:34, 109kB/s]
16%|#5 | 6.63M/41.5M [01:07<07:15, 83.9kB/s]
16%|#6 | 6.67M/41.5M [01:07<05:05, 120kB/s]
16%|#6 | 6.69M/41.5M [01:07<05:24, 113kB/s]
16%|#6 | 6.70M/41.5M [01:08<07:12, 84.3kB/s]
16%|#6 | 6.73M/41.5M [01:08<06:12, 97.9kB/s]
16%|#6 | 6.74M/41.5M [01:08<06:21, 95.4kB/s]
16%|#6 | 6.76M/41.5M [01:08<06:25, 94.6kB/s]
16%|#6 | 6.77M/41.5M [01:09<07:03, 85.9kB/s]
16%|#6 | 6.79M/41.5M [01:09<06:55, 87.5kB/s]
16%|#6 | 6.80M/41.5M [01:09<06:49, 88.8kB/s]
16%|#6 | 6.82M/41.5M [01:09<06:44, 89.8kB/s]
16%|#6 | 6.84M/41.5M [01:09<08:23, 72.2kB/s]
17%|#6 | 6.85M/41.5M [01:10<07:19, 82.7kB/s]
17%|#6 | 6.87M/41.5M [01:10<07:05, 85.3kB/s]
17%|#6 | 6.88M/41.5M [01:10<07:00, 86.2kB/s]
17%|#6 | 6.90M/41.5M [01:10<06:52, 87.9kB/s]
17%|#6 | 6.91M/41.5M [01:10<
06:41, 90.3kB/s]
17%|#6 | 6.93M/41.5M [01:10<06:38, 90.8kB/s]
17%|#6 | 6.95M/41.5M [01:11<05:50, 103kB/s]
17%|#6 | 6.97M/41.5M [01:11<06:00, 100kB/s]
17%|#6 | 6.98M/41.5M [01:11<06:09, 97.9kB/s]
17%|#6 | 7.00M/41.5M [01:11<06:10, 97.5kB/s]
17%|#6 | 7.02M/41.5M [01:11<05:38, 107kB/s]
17%|#6 | 7.03M/41.5M [01:12<08:33, 70.3kB/s]
17%|#6 | 7.05M/41.5M [01:12<07:12, 83.5kB/s]
17%|#7 | 7.08M/41.5M [01:12<05:23, 111kB/s]
17%|#7 | 7.09M/41.5M [01:12<05:40, 106kB/s]
17%|#7 | 7.11M/41.5M [01:12<05:53, 102kB/s]
17%|#7 | 7.12M/41.5M [01:12<06:03, 99.2kB/s]
17%|#7 | 7.14M/41.5M [01:13<08:25, 71.2kB/s]
17%|#7 | 7.18M/41.5M [01:13<05:12, 115kB/s]
17%|#7 | 7.20M/41.5M [01:13<05:52, 102kB/s]
17%|#7 | 7.21M/41.5M [01:13<05:36, 107kB/s]
17%|#7 | 7.23M/41.5M [01:14<05:49, 103kB/s]
17%|#7
| 7.24M/41.5M [01:14<06:00, 99.7kB/s]
17%|#7 | 7.26M/41.5M [01:14<05:31, 108kB/s]
18%|#7 | 7.27M/41.5M [01:14<05:18, 113kB/s]
18%|#7 | 7.29M/41.5M [01:14<05:24, 111kB/s]
18%|#7 | 7.30M/41.5M [01:14<07:06, 84.0kB/s]
18%|#7 | 7.34M/41.5M [01:15<05:55, 101kB/s]
18%|#7 | 7.35M/41.5M [01:15<06:03, 98.5kB/s]
18%|#7 | 7.37M/41.5M [01:15<06:09, 96.8kB/s]
18%|#7 | 7.39M/41.5M [01:15<05:29, 108kB/s]
18%|#7 | 7.41M/41.5M [01:15<05:44, 104kB/s]
18%|#7 | 7.42M/41.5M [01:15<05:14, 113kB/s]
18%|#7 | 7.44M/41.5M [01:16<04:58, 120kB/s]
18%|#7 | 7.45M/41.5M [01:16<05:23, 110kB/s]
18%|#8 | 7.47M/41.5M [01:16<07:31, 79.1kB/s]
18%|#8 | 7.50M/41.5M [01:16<05:13, 114kB/s]
18%|#8 | 7.52M/41.5M [01:17<05:55, 100kB/s]
18%|#8 | 7.53M/41.5M [01:17<06:03, 98.0kB/s]
18%|#8 | 7.55M/41.5M [01:17<07:53, 75.1k
B/s]
18%|#8 | 7.58M/41.5M [01:17<05:29, 108kB/s]
18%|#8 | 7.59M/41.5M [01:17<06:06, 97.0kB/s]
18%|#8 | 7.61M/41.5M [01:18<06:32, 90.4kB/s]
18%|#8 | 7.62M/41.5M [01:18<06:30, 90.9kB/s]
18%|#8 | 7.64M/41.5M [01:18<06:29, 91.2kB/s]
18%|#8 | 7.66M/41.5M [01:18<06:27, 91.6kB/s]
18%|#8 | 7.67M/41.5M [01:18<06:26, 91.8kB/s]
19%|#8 | 7.69M/41.5M [01:18<06:25, 91.9kB/s]
19%|#8 | 7.71M/41.5M [01:19<06:26, 91.7kB/s]
19%|#8 | 7.73M/41.5M [01:19<05:40, 104kB/s]
19%|#8 | 7.75M/41.5M [01:19<05:50, 101kB/s]
19%|#8 | 7.77M/41.5M [01:19<07:41, 76.6kB/s]
19%|#8 | 7.80M/41.5M [01:20<05:44, 102kB/s]
19%|#8 | 7.82M/41.5M [01:20<05:16, 112kB/s]
19%|#8 | 7.84M/41.5M [01:20<05:31, 106kB/s]
19%|#8 | 7.85M/41.5M [01:20<05:43, 103kB/s]
19%|#8 | 7.87M/41.5M [01:21<07:58, 73.7kB/s]
19%|#9 | 7.90M/
41.5M [01:21<08:19, 70.5kB/s]
19%|#9 | 7.93M/41.5M [01:21<06:21, 92.1kB/s]
19%|#9 | 7.95M/41.5M [01:21<06:21, 92.1kB/s]
19%|#9 | 7.96M/41.5M [01:22<06:21, 92.2kB/s]
19%|#9 | 7.98M/41.5M [01:22<09:31, 61.5kB/s]
19%|#9 | 8.00M/41.5M [01:22<07:40, 76.3kB/s]
19%|#9 | 8.02M/41.5M [01:23<07:20, 79.6kB/s]
19%|#9 | 8.03M/41.5M [01:23<08:44, 66.9kB/s]
19%|#9 | 8.05M/41.5M [01:23<08:04, 72.3kB/s]
19%|#9 | 8.06M/41.5M [01:23<07:35, 77.0kB/s]
19%|#9 | 8.08M/41.5M [01:23<07:13, 80.8kB/s]
20%|#9 | 8.09M/41.5M [01:24<08:48, 66.3kB/s]
20%|#9 | 8.12M/41.5M [01:24<07:02, 82.8kB/s]
20%|#9 | 8.13M/41.5M [01:24<07:14, 80.5kB/s]
20%|#9 | 8.15M/41.5M [01:24<08:19, 70.0kB/s]
20%|#9 | 8.16M/41.5M [01:25<07:44, 75.2kB/s]
20%|#9 | 8.18M/41.5M [01:25<07:19, 79.4kB/s]
20%|#9 | 8.20M/41.5M [01:25<07:01, 82.8kB/s
]
20%|#9 | 8.21M/41.5M [01:25<07:14, 80.3kB/s]
20%|#9 | 8.23M/41.5M [01:25<06:57, 83.5kB/s]
20%|#9 | 8.24M/41.5M [01:26<06:45, 85.9kB/s]
20%|#9 | 8.26M/41.5M [01:26<06:37, 87.7kB/s]
20%|#9 | 8.27M/41.5M [01:26<06:31, 89.0kB/s]
20%|#9 | 8.29M/41.5M [01:26<06:26, 90.0kB/s]
20%|## | 8.30M/41.5M [01:26<06:23, 90.6kB/s]
20%|## | 8.32M/41.5M [01:26<06:21, 91.1kB/s]
20%|## | 8.34M/41.5M [01:27<05:54, 98.2kB/s]
20%|## | 8.35M/41.5M [01:27<06:00, 96.3kB/s]
20%|## | 8.37M/41.5M [01:27<06:05, 95.1kB/s]
20%|## | 8.38M/41.5M [01:27<08:02, 72.0kB/s]
20%|## | 8.42M/41.5M [01:27<05:10, 112kB/s]
20%|## | 8.44M/41.5M [01:28<05:25, 107kB/s]
20%|## | 8.46M/41.5M [01:28<05:19, 108kB/s]
20%|## | 8.48M/41.5M [01:28<07:02, 81.9kB/s]
21%|## | 8.52M/41.5M [01:28<04:56, 117kB/s]
21%|## | 8.53M/4
1.5M [01:29<05:12, 110kB/s]
21%|## | 8.55M/41.5M [01:29<05:07, 112kB/s]
21%|## | 8.56M/41.5M [01:29<05:23, 107kB/s]
21%|## | 8.59M/41.5M [01:29<04:57, 116kB/s]
21%|## | 8.60M/41.5M [01:29<05:16, 109kB/s]
21%|## | 8.62M/41.5M [01:29<04:52, 118kB/s]
21%|## | 8.65M/41.5M [01:30<04:38, 124kB/s]
21%|## | 8.67M/41.5M [01:30<04:28, 128kB/s]
21%|## | 8.69M/41.5M [01:30<06:20, 90.4kB/s]
21%|##1 | 8.73M/41.5M [01:30<04:50, 118kB/s]
21%|##1 | 8.74M/41.5M [01:31<05:07, 112kB/s]
21%|##1 | 8.76M/41.5M [01:31<05:02, 114kB/s]
21%|##1 | 8.78M/41.5M [01:31<05:03, 113kB/s]
21%|##1 | 8.80M/41.5M [01:31<04:58, 115kB/s]
21%|##1 | 8.81M/41.5M [01:31<06:51, 83.2kB/s]
21%|##1 | 8.85M/41.5M [01:32<05:02, 113kB/s]
21%|##1 | 8.87M/41.5M [01:32<05:17, 108kB/s]
21%|##1 | 8.89M/41.5M [01:32<04:55, 116kB/s]
21%|##1
| 8.91M/41.5M [01:32<04:58, 114kB/s]
22%|##1 | 8.93M/41.5M [01:32<04:54, 116kB/s]
22%|##1 | 8.95M/41.5M [01:32<04:38, 122kB/s]
22%|##1 | 8.98M/41.5M [01:33<04:46, 119kB/s]
22%|##1 | 8.99M/41.5M [01:33<06:32, 86.8kB/s]
22%|##1 | 9.03M/41.5M [01:33<04:40, 121kB/s]
22%|##1 | 9.05M/41.5M [01:34<05:57, 95.2kB/s]
22%|##1 | 9.07M/41.5M [01:34<05:40, 99.7kB/s]
22%|##1 | 9.09M/41.5M [01:34<05:46, 97.9kB/s]
22%|##1 | 9.10M/41.5M [01:34<05:51, 96.5kB/s]
22%|##1 | 9.12M/41.5M [01:34<05:55, 95.4kB/s]
22%|##2 | 9.13M/41.5M [01:34<05:59, 94.5kB/s]
22%|##2 | 9.15M/41.5M [01:35<06:01, 93.9kB/s]
22%|##2 | 9.16M/41.5M [01:35<06:02, 93.4kB/s]
22%|##2 | 9.18M/41.5M [01:35<06:04, 93.1kB/s]
22%|##2 | 9.20M/41.5M [01:35<07:52, 71.6kB/s]
22%|##2 | 9.20M/41.5M [01:36<09:14, 61.1kB/s]
22%|##2 | 9.22M/41.5M [01:36<09:38
, 58.5kB/s]
22%|##2 | 9.25M/41.5M [01:36<06:52, 82.0kB/s]
22%|##2 | 9.27M/41.5M [01:36<08:14, 68.3kB/s]
22%|##2 | 9.27M/41.5M [01:37<08:51, 63.6kB/s]
22%|##2 | 9.29M/41.5M [01:37<08:00, 70.3kB/s]
22%|##2 | 9.30M/41.5M [01:37<08:45, 64.2kB/s]
22%|##2 | 9.30M/41.5M [01:37<09:27, 59.5kB/s]
22%|##2 | 9.32M/41.5M [01:37<08:12, 68.4kB/s]
23%|##2 | 9.34M/41.5M [01:38<07:29, 75.1kB/s]
23%|##2 | 9.34M/41.5M [01:38<08:24, 66.8kB/s]
23%|##2 | 9.36M/41.5M [01:38<07:33, 74.2kB/s]
23%|##2 | 9.38M/41.5M [01:38<09:08, 61.4kB/s]
23%|##2 | 9.41M/41.5M [01:38<06:07, 91.5kB/s]
23%|##2 | 9.42M/41.5M [01:39<06:30, 86.1kB/s]
23%|##2 | 9.44M/41.5M [01:39<08:01, 69.7kB/s]
23%|##2 | 9.45M/41.5M [01:39<07:04, 79.2kB/s]
23%|##2 | 9.47M/41.5M [01:40<08:30, 65.8kB/s]
23%|##2 | 9.48M/41.5M [01:40<09:07, 61.3kB/s]
23%|##2
| 9.49M/41.5M [01:40<08:07, 68.8kB/s]
23%|##2 | 9.50M/41.5M [01:40<08:52, 63.0kB/s]
23%|##2 | 9.52M/41.5M [01:40<07:53, 70.9kB/s]
23%|##2 | 9.53M/41.5M [01:40<07:16, 76.8kB/s]
23%|##3 | 9.55M/41.5M [01:41<06:52, 81.2kB/s]
23%|##3 | 9.56M/41.5M [01:41<06:36, 84.4kB/s]
23%|##3 | 9.58M/41.5M [01:41<06:25, 86.7kB/s]
23%|##3 | 9.59M/41.5M [01:41<06:18, 88.3kB/s]
23%|##3 | 9.61M/41.5M [01:41<06:13, 89.5kB/s]
23%|##3 | 9.62M/41.5M [01:42<08:00, 69.5kB/s]
23%|##3 | 9.66M/41.5M [01:42<05:41, 97.9kB/s]
23%|##3 | 9.67M/41.5M [01:42<05:46, 96.4kB/s]
23%|##3 | 9.69M/41.5M [01:42<05:49, 95.3kB/s]
23%|##3 | 9.70M/41.5M [01:42<05:52, 94.4kB/s]
23%|##3 | 9.72M/41.5M [01:43<05:55, 93.8kB/s]
23%|##3 | 9.73M/41.5M [01:43<05:56, 93.4kB/s]
24%|##3 | 9.76M/41.5M [01:43<05:12, 107kB/s]
24%|##3 | 9.77M/41.5M [01:43<05:2
5, 102kB/s]
24%|##3 | 9.79M/41.5M [01:43<05:34, 99.3kB/s]
24%|##3 | 9.81M/41.5M [01:43<04:59, 111kB/s]
24%|##3 | 9.83M/41.5M [01:44<05:36, 98.6kB/s]
24%|##3 | 9.84M/41.5M [01:44<05:42, 96.8kB/s]
24%|##3 | 9.86M/41.5M [01:44<05:24, 102kB/s]
24%|##3 | 9.88M/41.5M [01:44<05:34, 99.2kB/s]
24%|##3 | 9.89M/41.5M [01:44<05:41, 97.1kB/s]
24%|##3 | 9.91M/41.5M [01:44<05:46, 95.6kB/s]
24%|##3 | 9.92M/41.5M [01:45<05:49, 94.6kB/s]
24%|##3 | 9.94M/41.5M [01:45<07:39, 72.0kB/s]
24%|##4 | 9.97M/41.5M [01:45<05:30, 100kB/s]
24%|##4 | 9.98M/41.5M [01:45<05:37, 98.0kB/s]
24%|##4 | 10.0M/41.5M [01:46<05:42, 96.4kB/s]
24%|##4 | 10.0M/41.5M [01:46<05:46, 95.2kB/s]
24%|##4 | 10.0M/41.5M [01:46<07:52, 69.9kB/s]
24%|##4 | 10.1M/41.5M [01:46<05:24, 102kB/s]
24%|##4 | 10.1M/41.5M [01:47<06:32, 83.9kB/s]
24%|##4
| 10.1M/41.5M [01:47<06:23, 85.9kB/s]
24%|##4 | 10.1M/41.5M [01:47<06:15, 87.5kB/s]
24%|##4 | 10.1M/41.5M [01:47<05:25, 101kB/s]
24%|##4 | 10.1M/41.5M [01:47<05:33, 98.6kB/s]
24%|##4 | 10.2M/41.5M [01:47<05:39, 96.8kB/s]
25%|##4 | 10.2M/41.5M [01:48<05:01, 109kB/s]
25%|##4 | 10.2M/41.5M [01:48<05:15, 104kB/s]
25%|##4 | 10.2M/41.5M [01:48<04:47, 114kB/s]
25%|##4 | 10.2M/41.5M [01:48<05:04, 108kB/s]
25%|##4 | 10.3M/41.5M [01:48<05:18, 103kB/s]
25%|##4 | 10.3M/41.5M [01:49<04:48, 114kB/s]
25%|##4 | 10.3M/41.5M [01:49<05:05, 107kB/s]
25%|##4 | 10.3M/41.5M [01:49<04:40, 116kB/s]
25%|##4 | 10.3M/41.5M [01:49<04:25, 123kB/s]
25%|##4 | 10.4M/41.5M [01:49<04:15, 128kB/s]
25%|##5 | 10.4M/41.5M [01:49<04:09, 131kB/s]
25%|##5 | 10.4M/41.5M [01:50<04:04, 133kB/s]
25%|##5 | 10.4M/41.5M [01:50<04:01, 135kB/s]
25%|##5 | 10.5M/41.5M [01:50<03:37, 150kB/s]
25%|##5 | 10.5M/41.5M [01:50<03:42, 146kB/s]
25%|##5 | 10.5M/41.5M [01:50<03:45, 144kB/s]
25%|##5 | 10.5M/41.5M [01:50<03:28, 156kB/s]
25%|##5 | 10.6M/41.5M [01:51<03:35, 151kB/s]
26%|##5 | 10.6M/41.5M [01:51<03:21, 161kB/s]
26%|##5 | 10.6M/41.5M [01:51<03:15, 166kB/s]
26%|##5 | 10.7M/41.5M [01:51<03:08, 172kB/s]
26%|##5 | 10.7M/41.5M [01:51<03:03, 176kB/s]
26%|##5 | 10.7M/41.5M [01:52<03:00, 178kB/s]
26%|##5 | 10.8M/41.5M [01:52<02:45, 194kB/s]
26%|##6 | 10.8M/41.5M [01:52<02:35, 207kB/s]
26%|##6 | 10.8M/41.5M [01:52<02:41, 200kB/s]
26%|##6 | 10.8M/41.5M [01:52<03:27, 155kB/s]
26%|##6 | 10.9M/41.5M [01:52<03:14, 165kB/s]
26%|##6 | 10.9M/41.5M [01:53<02:34, 207kB/s]
26%|##6 | 11.0M/41.5M [01:53<02:50, 188kB/s]
26%|##6 | 11.0M/41.5M [01:53<03:0
3, 174kB/s]
27%|##6 | 11.0M/41.5M [01:53<03:15, 164kB/s]
27%|##6 | 11.0M/41.5M [01:53<03:07, 170kB/s]
27%|##6 | 11.1M/41.5M [01:54<03:18, 161kB/s]
27%|##6 | 11.1M/41.5M [01:54<03:10, 168kB/s]
27%|##6 | 11.1M/41.5M [01:54<03:20, 159kB/s]
27%|##6 | 11.1M/41.5M [01:54<03:13, 165kB/s]
27%|##6 | 11.2M/41.5M [01:54<03:04, 172kB/s]
27%|##6 | 11.2M/41.5M [01:54<03:02, 175kB/s]
27%|##7 | 11.2M/41.5M [01:55<04:22, 121kB/s]
27%|##7 | 11.3M/41.5M [01:55<03:03, 173kB/s]
27%|##7 | 11.3M/41.5M [01:55<04:10, 127kB/s]
27%|##7 | 11.3M/41.5M [01:55<03:45, 141kB/s]
27%|##7 | 11.3M/41.5M [01:56<04:13, 125kB/s]
27%|##7 | 11.4M/41.5M [01:56<04:31, 117kB/s]
27%|##7 | 11.4M/41.5M [01:56<04:27, 118kB/s]
27%|##7 | 11.4M/41.5M [01:56<04:26, 118kB/s]
27%|##7 | 11.4M/41.5M [01:56<04:45, 111kB/s]
28%|##7 | 11.4M/41.5M
[01:56<05:00, 105kB/s]
28%|##7 | 11.4M/41.5M [01:57<04:33, 115kB/s]
28%|##7 | 11.5M/41.5M [01:57<04:51, 108kB/s]
28%|##7 | 11.5M/41.5M [01:57<04:28, 117kB/s]
28%|##7 | 11.5M/41.5M [01:57<04:31, 116kB/s]
28%|##7 | 11.5M/41.5M [01:57<04:17, 122kB/s]
28%|##7 | 11.5M/41.5M [01:58<04:07, 127kB/s]
28%|##7 | 11.6M/41.5M [01:58<04:10, 125kB/s]
28%|##7 | 11.6M/41.5M [01:58<03:53, 134kB/s]
28%|##8 | 11.6M/41.5M [01:58<03:51, 135kB/s]
28%|##8 | 11.6M/41.5M [01:58<03:49, 136kB/s]
28%|##8 | 11.7M/41.5M [01:58<03:33, 147kB/s]
28%|##8 | 11.7M/41.5M [01:59<03:36, 144kB/s]
28%|##8 | 11.7M/41.5M [01:59<03:19, 157kB/s]
28%|##8 | 11.7M/41.5M [01:59<04:44, 110kB/s]
28%|##8 | 11.8M/41.5M [01:59<03:13, 161kB/s]
28%|##8 | 11.8M/41.5M [01:59<03:20, 155kB/s]
29%|##8 | 11.8M/41.5M [02:00<03:26, 151kB/s]
29%|##8 | 1
1.9M/41.5M [02:00<03:17, 157kB/s]
29%|##8 | 11.9M/41.5M [02:00<03:24, 151kB/s]
29%|##8 | 11.9M/41.5M [02:00<03:24, 151kB/s]
29%|##8 | 12.0M/41.5M [02:00<03:12, 161kB/s]
29%|##8 | 12.0M/41.5M [02:01<03:04, 168kB/s]
29%|##8 | 12.0M/41.5M [02:01<03:01, 170kB/s]
29%|##8 | 12.0M/41.5M [02:01<02:56, 175kB/s]
29%|##9 | 12.1M/41.5M [02:01<02:53, 178kB/s]
29%|##9 | 12.1M/41.5M [02:01<02:51, 180kB/s]
29%|##9 | 12.1M/41.5M [02:01<03:06, 166kB/s]
29%|##9 | 12.1M/41.5M [02:01<03:16, 157kB/s]
29%|##9 | 12.2M/41.5M [02:02<03:05, 166kB/s]
29%|##9 | 12.2M/41.5M [02:02<02:59, 171kB/s]
29%|##9 | 12.2M/41.5M [02:02<02:54, 176kB/s]
30%|##9 | 12.2M/41.5M [02:02<03:06, 164kB/s]
30%|##9 | 12.3M/41.5M [02:02<02:46, 184kB/s]
30%|##9 | 12.3M/41.5M [02:02<02:45, 184kB/s]
30%|##9 | 12.3M/41.5M [02:03<03:13, 158kB/s]
30%|##
9 | 12.4M/41.5M [02:03<02:50, 179kB/s]
30%|##9 | 12.4M/41.5M [02:03<03:03, 166kB/s]
30%|##9 | 12.4M/41.5M [02:03<02:57, 172kB/s]
30%|##9 | 12.4M/41.5M [02:04<04:05, 124kB/s]
30%|### | 12.5M/41.5M [02:04<02:55, 174kB/s]
30%|### | 12.5M/41.5M [02:04<03:04, 164kB/s]
30%|### | 12.5M/41.5M [02:04<04:05, 124kB/s]
30%|### | 12.6M/41.5M [02:04<03:23, 149kB/s]
30%|### | 12.6M/41.5M [02:05<03:27, 146kB/s]
30%|### | 12.6M/41.5M [02:05<03:49, 132kB/s]
30%|### | 12.6M/41.5M [02:05<05:18, 94.9kB/s]
31%|### | 12.7M/41.5M [02:05<03:58, 127kB/s]
31%|### | 12.7M/41.5M [02:06<04:08, 122kB/s]
31%|### | 12.7M/41.5M [02:06<04:21, 115kB/s]
31%|### | 12.7M/41.5M [02:06<04:19, 116kB/s]
31%|### | 12.8M/41.5M [02:06<04:24, 114kB/s]
31%|### | 12.8M/41.5M [02:06<04:36, 109kB/s]
31%|### | 12.8M/41.5M [02:06<04:31, 111kB/s
]
31%|### | 12.8M/41.5M [02:07<04:28, 112kB/s]
31%|### | 12.8M/41.5M [02:07<06:04, 82.4kB/s]
31%|###1 | 12.9M/41.5M [02:07<04:15, 117kB/s]
31%|###1 | 12.9M/41.5M [02:07<04:30, 111kB/s]
31%|###1 | 12.9M/41.5M [02:07<04:43, 106kB/s]
31%|###1 | 12.9M/41.5M [02:08<04:20, 115kB/s]
31%|###1 | 12.9M/41.5M [02:08<04:35, 108kB/s]
31%|###1 | 13.0M/41.5M [02:08<04:15, 117kB/s]
31%|###1 | 13.0M/41.5M [02:08<04:02, 123kB/s]
31%|###1 | 13.0M/41.5M [02:08<03:53, 128kB/s]
31%|###1 | 13.0M/41.5M [02:09<04:14, 117kB/s]
31%|###1 | 13.0M/41.5M [02:09<05:13, 95.0kB/s]
32%|###1 | 13.1M/41.5M [02:09<03:51, 128kB/s]
32%|###1 | 13.1M/41.5M [02:09<04:09, 119kB/s]
32%|###1 | 13.1M/41.5M [02:09<04:26, 112kB/s]
32%|###1 | 13.1M/41.5M [02:10<04:39, 106kB/s]
32%|###1 | 13.1M/41.5M [02:10<04:50, 102kB/s]
32%|###1 | 13.2M/41.5M [02:10
<04:23, 113kB/s]
32%|###1 | 13.2M/41.5M [02:10<04:06, 120kB/s]
32%|###1 | 13.2M/41.5M [02:10<03:56, 126kB/s]
32%|###1 | 13.2M/41.5M [02:11<03:49, 129kB/s]
32%|###1 | 13.3M/41.5M [02:11<05:24, 91.1kB/s]
32%|###2 | 13.3M/41.5M [02:11<03:55, 126kB/s]
32%|###2 | 13.3M/41.5M [02:11<04:12, 117kB/s]
32%|###2 | 13.3M/41.5M [02:11<04:27, 110kB/s]
32%|###2 | 13.3M/41.5M [02:12<05:59, 82.1kB/s]
32%|###2 | 13.4M/41.5M [02:12<04:11, 117kB/s]
32%|###2 | 13.4M/41.5M [02:12<04:25, 111kB/s]
32%|###2 | 13.4M/41.5M [02:12<04:37, 106kB/s]
32%|###2 | 13.4M/41.5M [02:13<06:26, 76.1kB/s]
32%|###2 | 13.5M/41.5M [02:13<05:08, 95.4kB/s]
32%|###2 | 13.5M/41.5M [02:13<05:29, 89.2kB/s]
33%|###2 | 13.5M/41.5M [02:13<05:26, 90.0kB/s]
33%|###2 | 13.5M/41.5M [02:14<07:57, 61.5kB/s]
33%|###2 | 13.5M/41.5M [02:14<05:37, 86.8kB/s]
33%|###2
| 13.5M/41.5M [02:14<05:32, 88.1kB/s]
33%|###2 | 13.6M/41.5M [02:14<06:49, 71.5kB/s]
33%|###2 | 13.6M/41.5M [02:15<06:54, 70.6kB/s]
33%|###2 | 13.6M/41.5M [02:15<06:27, 75.5kB/s]
33%|###2 | 13.6M/41.5M [02:15<07:05, 68.7kB/s]
33%|###2 | 13.6M/41.5M [02:16<10:04, 48.3kB/s]
33%|###2 | 13.6M/41.5M [02:16<07:30, 64.8kB/s]
33%|###2 | 13.6M/41.5M [02:16<08:00, 60.7kB/s]
33%|###2 | 13.7M/41.5M [02:16<07:07, 68.2kB/s]
33%|###2 | 13.7M/41.5M [02:16<07:45, 62.6kB/s]
33%|###2 | 13.7M/41.5M [02:16<06:53, 70.5kB/s]
33%|###3 | 13.7M/41.5M [02:17<07:36, 63.8kB/s]
33%|###3 | 13.7M/41.5M [02:17<08:15, 58.8kB/s]
33%|###3 | 13.7M/41.5M [02:17<11:10, 43.4kB/s]
33%|###3 | 13.8M/41.5M [02:18<06:41, 72.4kB/s]
33%|###3 | 13.8M/41.5M [02:18<07:22, 65.7kB/s]
33%|###3 | 13.8M/41.5M [02:18<06:46, 71.5kB/s]
33%|###3 | 13.8M/41.5M [02:18<06:41,
72.3kB/s]
33%|###3 | 13.8M/41.5M [02:18<06:16, 77.1kB/s]
33%|###3 | 13.8M/41.5M [02:19<05:58, 80.9kB/s]
33%|###3 | 13.8M/41.5M [02:19<05:45, 84.0kB/s]
33%|###3 | 13.9M/41.5M [02:19<05:35, 86.3kB/s]
33%|###3 | 13.9M/41.5M [02:19<05:29, 88.0kB/s]
33%|###3 | 13.9M/41.5M [02:19<05:24, 89.2kB/s]
34%|###3 | 13.9M/41.5M [02:20<06:54, 69.7kB/s]
34%|###3 | 13.9M/41.5M [02:20<05:34, 86.5kB/s]
34%|###3 | 13.9M/41.5M [02:20<05:48, 82.9kB/s]
34%|###3 | 14.0M/41.5M [02:20<05:17, 90.9kB/s]
34%|###3 | 14.0M/41.5M [02:20<05:15, 91.3kB/s]
34%|###3 | 14.0M/41.5M [02:21<05:14, 91.6kB/s]
34%|###3 | 14.0M/41.5M [02:21<05:13, 91.8kB/s]
34%|###3 | 14.0M/41.5M [02:21<05:13, 91.9kB/s]
34%|###3 | 14.0M/41.5M [02:21<06:45, 70.9kB/s]
34%|###3 | 14.1M/41.5M [02:21<04:50, 98.9kB/s]
34%|###3 | 14.1M/41.5M [02:22<05:14, 91.5kB/s]
34%|###3
| 14.1M/41.5M [02:22<05:13, 91.6kB/s]
34%|###4 | 14.1M/41.5M [02:22<04:52, 98.2kB/s]
34%|###4 | 14.1M/41.5M [02:22<04:57, 96.4kB/s]
34%|###4 | 14.1M/41.5M [02:22<05:01, 95.2kB/s]
34%|###4 | 14.2M/41.5M [02:23<05:03, 94.4kB/s]
34%|###4 | 14.2M/41.5M [02:23<05:05, 93.7kB/s]
34%|###4 | 14.2M/41.5M [02:23<06:38, 71.8kB/s]
34%|###4 | 14.2M/41.5M [02:23<05:24, 88.2kB/s]
34%|###4 | 14.2M/41.5M [02:23<05:20, 89.3kB/s]
34%|###4 | 14.2M/41.5M [02:24<05:17, 90.1kB/s]
34%|###4 | 14.3M/41.5M [02:24<05:14, 90.7kB/s]
34%|###4 | 14.3M/41.5M [02:24<05:13, 91.1kB/s]
34%|###4 | 14.3M/41.5M [02:24<05:11, 91.5kB/s]
34%|###4 | 14.3M/41.5M [02:24<05:10, 91.7kB/s]
35%|###4 | 14.3M/41.5M [02:24<05:10, 91.9kB/s]
35%|###4 | 14.3M/41.5M [02:25<05:09, 92.0kB/s]
35%|###4 | 14.4M/41.5M [02:25<04:28, 106kB/s]
35%|###4 | 14.4M/41.5M [02:25<04:39
, 102kB/s]
35%|###4 | 14.4M/41.5M [02:25<04:47, 98.9kB/s]
35%|###4 | 14.4M/41.5M [02:25<04:16, 111kB/s]
35%|###4 | 14.4M/41.5M [02:26<06:10, 76.6kB/s]
35%|###4 | 14.5M/41.5M [02:26<05:32, 85.2kB/s]
35%|###4 | 14.5M/41.5M [02:26<03:48, 124kB/s]
35%|###4 | 14.5M/41.5M [02:26<04:05, 115kB/s]
35%|###5 | 14.5M/41.5M [02:26<04:20, 109kB/s]
35%|###5 | 14.5M/41.5M [02:27<04:01, 117kB/s]
35%|###5 | 14.6M/41.5M [02:27<04:16, 110kB/s]
35%|###5 | 14.6M/41.5M [02:27<03:58, 118kB/s]
35%|###5 | 14.6M/41.5M [02:27<05:30, 85.3kB/s]
35%|###5 | 14.6M/41.5M [02:27<03:52, 121kB/s]
35%|###5 | 14.7M/41.5M [02:28<04:07, 113kB/s]
35%|###5 | 14.7M/41.5M [02:28<04:21, 108kB/s]
35%|###5 | 14.7M/41.5M [02:28<04:01, 116kB/s]
35%|###5 | 14.7M/41.5M [02:28<04:16, 109kB/s]
36%|###5 | 14.7M/41.5M [02:28<03:58, 118kB/s]
36%|###5 | 14.8M/
41.5M [02:29<03:46, 124kB/s]
36%|###5 | 14.8M/41.5M [02:29<04:04, 115kB/s]
36%|###5 | 14.8M/41.5M [02:29<03:50, 122kB/s]
36%|###5 | 14.8M/41.5M [02:29<04:43, 98.6kB/s]
36%|###5 | 14.8M/41.5M [02:29<03:34, 130kB/s]
36%|###5 | 14.9M/41.5M [02:29<03:54, 119kB/s]
36%|###5 | 14.9M/41.5M [02:30<04:10, 111kB/s]
36%|###5 | 14.9M/41.5M [02:30<04:23, 106kB/s]
36%|###5 | 14.9M/41.5M [02:30<04:14, 110kB/s]
36%|###5 | 14.9M/41.5M [02:30<05:29, 84.7kB/s]
36%|###6 | 15.0M/41.5M [02:31<04:16, 109kB/s]
36%|###6 | 15.0M/41.5M [02:31<04:25, 105kB/s]
36%|###6 | 15.0M/41.5M [02:31<04:33, 102kB/s]
36%|###6 | 15.0M/41.5M [02:31<04:09, 111kB/s]
36%|###6 | 15.0M/41.5M [02:31<04:20, 106kB/s]
36%|###6 | 15.1M/41.5M [02:31<03:59, 116kB/s]
36%|###6 | 15.1M/41.5M [02:32<03:46, 122kB/s]
36%|###6 | 15.1M/41.5M [02:32<04:04, 113kB/s]
36%|###
6 | 15.1M/41.5M [02:32<03:48, 121kB/s]
36%|###6 | 15.1M/41.5M [02:32<03:39, 126kB/s]
37%|###6 | 15.2M/41.5M [02:32<03:32, 130kB/s]
37%|###6 | 15.2M/41.5M [02:33<03:28, 132kB/s]
37%|###6 | 15.2M/41.5M [02:33<03:49, 120kB/s]
37%|###6 | 15.2M/41.5M [02:33<03:17, 139kB/s]
37%|###6 | 15.3M/41.5M [02:33<03:18, 139kB/s]
37%|###6 | 15.3M/41.5M [02:33<03:17, 139kB/s]
37%|###6 | 15.3M/41.5M [02:33<03:17, 139kB/s]
37%|###6 | 15.3M/41.5M [02:34<03:17, 139kB/s]
37%|###6 | 15.3M/41.5M [02:34<03:40, 124kB/s]
37%|###7 | 15.4M/41.5M [02:34<03:11, 143kB/s]
37%|###7 | 15.4M/41.5M [02:34<03:13, 141kB/s]
37%|###7 | 15.4M/41.5M [02:34<03:35, 127kB/s]
37%|###7 | 15.4M/41.5M [02:34<03:09, 144kB/s]
37%|###7 | 15.5M/41.5M [02:35<03:11, 142kB/s]
37%|###7 | 15.5M/41.5M [02:35<03:13, 141kB/s]
37%|###7 | 15.5M/41.5M [02:35<03:14, 140kB/s]
37%|###7 | 15.5M/41.5M [02:35<02:57, 153kB/s]
38%|###7 | 15.6M/41.5M [02:35<03:22, 135kB/s]
38%|###7 | 15.6M/41.5M [02:36<03:01, 150kB/s]
38%|###7 | 15.6M/41.5M [02:36<03:05, 146kB/s]
38%|###7 | 15.6M/41.5M [02:36<03:28, 130kB/s]
38%|###7 | 15.6M/41.5M [02:36<03:48, 118kB/s]
38%|###7 | 15.7M/41.5M [02:36<03:37, 125kB/s]
38%|###7 | 15.7M/41.5M [02:37<05:06, 88.1kB/s]
38%|###7 | 15.7M/41.5M [02:37<04:28, 101kB/s]
38%|###7 | 15.7M/41.5M [02:37<04:34, 98.5kB/s]
38%|###7 | 15.7M/41.5M [02:37<04:38, 96.8kB/s]
38%|###7 | 15.8M/41.5M [02:37<04:42, 95.5kB/s]
38%|###8 | 15.8M/41.5M [02:38<07:28, 60.2kB/s]
38%|###8 | 15.8M/41.5M [02:38<05:14, 85.8kB/s]
38%|###8 | 15.8M/41.5M [02:38<05:08, 87.2kB/s]
38%|###8 | 15.8M/41.5M [02:38<05:04, 88.5kB/s]
38%|###8 | 15.9M/41.5M [02:39<05:00, 89.5kB/s]
38%|###8 | 15.9M/41.5M [02
:39<04:57, 90.2kB/s]
38%|###8 | 15.9M/41.5M [02:39<04:55, 90.8kB/s]
38%|###8 | 15.9M/41.5M [02:39<04:54, 91.2kB/s]
38%|###8 | 15.9M/41.5M [02:39<04:52, 91.5kB/s]
38%|###8 | 15.9M/41.5M [02:39<04:52, 91.7kB/s]
38%|###8 | 15.9M/41.5M [02:40<04:51, 91.9kB/s]
38%|###8 | 16.0M/41.5M [02:40<04:50, 92.0kB/s]
39%|###8 | 16.0M/41.5M [02:40<04:50, 92.1kB/s]
39%|###8 | 16.0M/41.5M [02:40<04:50, 92.1kB/s]
39%|###8 | 16.0M/41.5M [02:40<04:12, 106kB/s]
39%|###8 | 16.0M/41.5M [02:40<04:22, 102kB/s]
39%|###8 | 16.1M/41.5M [02:41<03:56, 113kB/s]
39%|###8 | 16.1M/41.5M [02:41<03:41, 120kB/s]
39%|###8 | 16.1M/41.5M [02:41<03:57, 112kB/s]
39%|###8 | 16.1M/41.5M [02:41<04:29, 98.9kB/s]
39%|###8 | 16.1M/41.5M [02:41<03:20, 132kB/s]
39%|###8 | 16.2M/41.5M [02:42<03:41, 120kB/s]
39%|###8 | 16.2M/41.5M [02:42<05:10, 85.6kB/s]
39%|###
9 | 16.2M/41.5M [02:42<06:20, 69.8kB/s]
39%|###9 | 16.2M/41.5M [02:42<04:38, 95.2kB/s]
39%|###9 | 16.2M/41.5M [02:43<04:40, 94.5kB/s]
39%|###9 | 16.2M/41.5M [02:43<04:41, 93.9kB/s]
39%|###9 | 16.3M/41.5M [02:43<04:43, 93.5kB/s]
39%|###9 | 16.3M/41.5M [02:43<06:39, 66.2kB/s]
39%|###9 | 16.3M/41.5M [02:44<05:20, 82.5kB/s]
39%|###9 | 16.3M/41.5M [02:44<05:11, 84.6kB/s]
39%|###9 | 16.3M/41.5M [02:44<05:05, 86.4kB/s]
39%|###9 | 16.4M/41.5M [02:45<07:31, 58.3kB/s]
40%|###9 | 16.4M/41.5M [02:45<07:21, 59.6kB/s]
40%|###9 | 16.4M/41.5M [02:45<05:27, 80.4kB/s]
40%|###9 | 16.4M/41.5M [02:45<05:17, 82.7kB/s]
40%|###9 | 16.5M/41.5M [02:46<06:16, 69.7kB/s]
40%|###9 | 16.5M/41.5M [02:46<05:53, 74.3kB/s]
40%|###9 | 16.5M/41.5M [02:46<05:34, 78.3kB/s]
40%|###9 | 16.5M/41.5M [02:46<05:20, 81.7kB/s]
40%|###9 | 16.5M/41.5M [02:47<
05:10, 84.2kB/s]
40%|###9 | 16.5M/41.5M [02:47<07:45, 56.2kB/s]
40%|###9 | 16.6M/41.5M [02:47<05:19, 81.7kB/s]
40%|###9 | 16.6M/41.5M [02:47<05:10, 84.0kB/s]
40%|###9 | 16.6M/41.5M [02:48<05:03, 86.0kB/s]
40%|#### | 16.6M/41.5M [02:48<04:57, 87.6kB/s]
40%|#### | 16.6M/41.5M [02:48<07:30, 57.9kB/s]
40%|#### | 16.7M/41.5M [02:48<05:13, 83.1kB/s]
40%|#### | 16.7M/41.5M [02:49<05:05, 85.2kB/s]
40%|#### | 16.7M/41.5M [02:49<04:59, 86.9kB/s]
40%|#### | 16.7M/41.5M [02:49<04:54, 88.2kB/s]
40%|#### | 16.7M/41.5M [02:49<04:50, 89.3kB/s]
40%|#### | 16.7M/41.5M [02:49<04:48, 90.0kB/s]
40%|#### | 16.8M/41.5M [02:50<04:46, 90.6kB/s]
40%|#### | 16.8M/41.5M [02:50<04:44, 91.1kB/s]
40%|#### | 16.8M/41.5M [02:50<04:43, 91.4kB/s]
40%|#### | 16.8M/41.5M [02:50<04:42, 91.7kB/s]
41%|#### | 16.8M/41.5M [02:50<04:41, 91.8kB/s]
41%|##
## | 16.8M/41.5M [02:50<04:41, 92.0kB/s]
41%|#### | 16.8M/41.5M [02:51<04:40, 92.1kB/s]
41%|#### | 16.9M/41.5M [02:51<04:03, 106kB/s]
41%|#### | 16.9M/41.5M [02:51<05:29, 78.3kB/s]
41%|#### | 16.9M/41.5M [02:51<04:06, 105kB/s]
41%|#### | 16.9M/41.5M [02:52<04:14, 101kB/s]
41%|#### | 16.9M/41.5M [02:52<04:20, 98.9kB/s]
41%|#### | 17.0M/41.5M [02:52<03:53, 110kB/s]
41%|#### | 17.0M/41.5M [02:52<04:05, 105kB/s]
41%|#### | 17.0M/41.5M [02:52<03:44, 115kB/s]
41%|####1 | 17.0M/41.5M [02:52<03:57, 108kB/s]
41%|####1 | 17.0M/41.5M [02:53<03:39, 117kB/s]
41%|####1 | 17.1M/41.5M [02:53<03:53, 110kB/s]
41%|####1 | 17.1M/41.5M [02:53<03:36, 118kB/s]
41%|####1 | 17.1M/41.5M [02:53<03:51, 110kB/s]
41%|####1 | 17.1M/41.5M [02:53<04:39, 91.3kB/s]
41%|####1 | 17.2M/41.5M [02:54<03:42, 114kB/s]
41%|####1 | 17.2M/41.5M [02:54<03:54,
109kB/s]
41%|####1 | 17.2M/41.5M [02:54<04:04, 104kB/s]
41%|####1 | 17.2M/41.5M [02:54<03:43, 114kB/s]
42%|####1 | 17.2M/41.5M [02:54<03:56, 108kB/s]
42%|####1 | 17.2M/41.5M [02:55<03:38, 117kB/s]
42%|####1 | 17.3M/41.5M [02:55<03:26, 123kB/s]
42%|####1 | 17.3M/41.5M [02:55<03:19, 127kB/s]
42%|####1 | 17.3M/41.5M [02:55<03:36, 117kB/s]
42%|####1 | 17.3M/41.5M [02:55<03:25, 123kB/s]
42%|####1 | 17.4M/41.5M [02:55<03:17, 128kB/s]
42%|####1 | 17.4M/41.5M [02:56<03:13, 131kB/s]
42%|####1 | 17.4M/41.5M [02:56<03:09, 133kB/s]
42%|####2 | 17.4M/41.5M [02:56<03:07, 135kB/s]
42%|####2 | 17.5M/41.5M [02:56<03:05, 136kB/s]
42%|####2 | 17.5M/41.5M [02:56<03:04, 137kB/s]
42%|####2 | 17.5M/41.5M [02:56<03:03, 137kB/s]
42%|####2 | 17.5M/41.5M [02:57<03:38, 115kB/s]
42%|####2 | 17.5M/41.5M [02:57<03:26, 122kB/s]
42%|####2 | 17.6M/41.5M [02
:57<04:30, 92.7kB/s]
42%|####2 | 17.6M/41.5M [02:57<04:47, 87.2kB/s]
42%|####2 | 17.6M/41.5M [02:58<03:43, 112kB/s]
42%|####2 | 17.6M/41.5M [02:58<03:54, 107kB/s]
42%|####2 | 17.6M/41.5M [02:58<04:03, 103kB/s]
43%|####2 | 17.6M/41.5M [02:58<04:10, 99.7kB/s]
43%|####2 | 17.7M/41.5M [02:58<04:16, 97.5kB/s]
43%|####2 | 17.7M/41.5M [02:58<04:20, 96.0kB/s]
43%|####2 | 17.7M/41.5M [02:59<04:22, 94.9kB/s]
43%|####2 | 17.7M/41.5M [02:59<04:24, 94.1kB/s]
43%|####2 | 17.7M/41.5M [02:59<07:04, 58.7kB/s]
43%|####2 | 17.8M/41.5M [03:00<04:34, 90.5kB/s]
43%|####2 | 17.8M/41.5M [03:00<06:35, 62.8kB/s]
43%|####2 | 17.8M/41.5M [03:00<04:27, 92.8kB/s]
43%|####2 | 17.8M/41.5M [03:00<04:27, 92.7kB/s]
43%|####3 | 17.9M/41.5M [03:01<04:27, 92.6kB/s]
43%|####3 | 17.9M/41.5M [03:01<05:33, 74.4kB/s]
43%|####3 | 17.9M/41.5M [03:01<05:16, 78.3kB/s]
43%|
####3 | 17.9M/41.5M [03:01<05:03, 81.6kB/s]
43%|####3 | 17.9M/41.5M [03:02<04:53, 84.2kB/s]
43%|####3 | 17.9M/41.5M [03:02<04:46, 86.3kB/s]
43%|####3 | 17.9M/41.5M [03:02<04:40, 88.0kB/s]
43%|####3 | 18.0M/41.5M [03:02<04:36, 89.2kB/s]
43%|####3 | 18.0M/41.5M [03:02<03:58, 103kB/s]
43%|####3 | 18.0M/41.5M [03:02<04:05, 100kB/s]
43%|####3 | 18.0M/41.5M [03:03<03:41, 111kB/s]
43%|####3 | 18.0M/41.5M [03:03<03:52, 106kB/s]
44%|####3 | 18.1M/41.5M [03:03<03:32, 115kB/s]
44%|####3 | 18.1M/41.5M [03:03<03:20, 122kB/s]
44%|####3 | 18.1M/41.5M [03:03<03:36, 113kB/s]
44%|####3 | 18.1M/41.5M [03:04<04:57, 82.3kB/s]
44%|####3 | 18.2M/41.5M [03:04<03:18, 123kB/s]
44%|####3 | 18.2M/41.5M [03:04<03:31, 116kB/s]
44%|####3 | 18.2M/41.5M [03:04<03:20, 122kB/s]
44%|####3 | 18.2M/41.5M [03:04<03:13, 126kB/s]
44%|####3 | 18.2M/41.5M [03:05<03:08,
130kB/s]
44%|####4 | 18.3M/41.5M [03:05<03:04, 132kB/s]
44%|####4 | 18.3M/41.5M [03:05<03:01, 134kB/s]
44%|####4 | 18.3M/41.5M [03:05<02:59, 135kB/s]
44%|####4 | 18.3M/41.5M [03:06<04:16, 94.5kB/s]
44%|####4 | 18.4M/41.5M [03:06<02:54, 139kB/s]
44%|####4 | 18.4M/41.5M [03:06<03:10, 127kB/s]
44%|####4 | 18.4M/41.5M [03:06<03:25, 118kB/s]
44%|####4 | 18.4M/41.5M [03:06<03:15, 123kB/s]
44%|####4 | 18.5M/41.5M [03:06<03:31, 114kB/s]
45%|####4 | 18.5M/41.5M [03:07<02:59, 135kB/s]
45%|####4 | 18.5M/41.5M [03:07<03:17, 122kB/s]
45%|####4 | 18.5M/41.5M [03:07<03:32, 113kB/s]
45%|####4 | 18.5M/41.5M [03:07<03:44, 107kB/s]
45%|####4 | 18.6M/41.5M [03:07<03:26, 116kB/s]
45%|####4 | 18.6M/41.5M [03:07<03:40, 109kB/s]
45%|####4 | 18.6M/41.5M [03:08<03:50, 104kB/s]
45%|####4 | 18.6M/41.5M [03:08<03:29, 114kB/s]
45%|####4 | 18.6M/41.5M
[03:08<03:42, 108kB/s]
45%|####4 | 18.6M/41.5M [03:08<03:24, 117kB/s]
45%|####5 | 18.7M/41.5M [03:08<03:14, 123kB/s]
45%|####5 | 18.7M/41.5M [03:09<03:06, 128kB/s]
45%|####5 | 18.7M/41.5M [03:09<03:02, 131kB/s]
45%|####5 | 18.7M/41.5M [03:09<02:59, 133kB/s]
45%|####5 | 18.8M/41.5M [03:09<02:56, 135kB/s]
45%|####5 | 18.8M/41.5M [03:09<03:29, 114kB/s]
45%|####5 | 18.8M/41.5M [03:09<03:03, 130kB/s]
45%|####5 | 18.8M/41.5M [03:10<03:20, 118kB/s]
45%|####5 | 18.8M/41.5M [03:10<03:10, 124kB/s]
45%|####5 | 18.9M/41.5M [03:10<03:04, 129kB/s]
46%|####5 | 18.9M/41.5M [03:10<03:00, 132kB/s]
46%|####5 | 18.9M/41.5M [03:10<02:57, 134kB/s]
46%|####5 | 18.9M/41.5M [03:10<02:55, 135kB/s]
46%|####5 | 19.0M/41.5M [03:11<02:53, 136kB/s]
46%|####5 | 19.0M/41.5M [03:11<02:52, 137kB/s]
46%|####5 | 19.0M/41.5M [03:11<02:36, 151kB/s]
46%|####5 | 1
9.0M/41.5M [03:11<02:39, 147kB/s]
46%|####5 | 19.1M/41.5M [03:11<02:42, 145kB/s]
46%|####6 | 19.1M/41.5M [03:12<02:44, 143kB/s]
46%|####6 | 19.1M/41.5M [03:12<02:31, 155kB/s]
46%|####6 | 19.1M/41.5M [03:12<02:35, 150kB/s]
46%|####6 | 19.2M/41.5M [03:12<02:25, 160kB/s]
46%|####6 | 19.2M/41.5M [03:12<02:31, 154kB/s]
46%|####6 | 19.2M/41.5M [03:12<02:23, 163kB/s]
46%|####6 | 19.2M/41.5M [03:13<02:29, 156kB/s]
46%|####6 | 19.3M/41.5M [03:13<03:02, 127kB/s]
47%|####6 | 19.3M/41.5M [03:13<02:18, 168kB/s]
47%|####6 | 19.3M/41.5M [03:13<02:26, 159kB/s]
47%|####6 | 19.4M/41.5M [03:13<02:31, 153kB/s]
47%|####6 | 19.4M/41.5M [03:14<02:22, 162kB/s]
47%|####6 | 19.4M/41.5M [03:14<02:29, 155kB/s]
47%|####6 | 19.4M/41.5M [03:14<02:20, 164kB/s]
47%|####6 | 19.5M/41.5M [03:14<02:15, 170kB/s]
47%|####6 | 19.5M/41.5M [03:14<02:12, 174kB/s]
47%|##
##7 | 19.5M/41.5M [03:14<02:40, 143kB/s]
47%|####7 | 19.6M/41.5M [03:15<02:07, 180kB/s]
47%|####7 | 19.6M/41.5M [03:15<02:16, 168kB/s]
47%|####7 | 19.6M/41.5M [03:15<02:23, 160kB/s]
47%|####7 | 19.6M/41.5M [03:15<02:19, 164kB/s]
47%|####7 | 19.7M/41.5M [03:15<02:15, 169kB/s]
47%|####7 | 19.7M/41.5M [03:15<02:23, 159kB/s]
48%|####7 | 19.7M/41.5M [03:16<02:16, 167kB/s]
48%|####7 | 19.7M/41.5M [03:16<02:11, 173kB/s]
48%|####7 | 19.8M/41.5M [03:16<02:09, 176kB/s]
48%|####7 | 19.8M/41.5M [03:16<02:08, 177kB/s]
48%|####7 | 19.8M/41.5M [03:16<02:07, 179kB/s]
48%|####7 | 19.8M/41.5M [03:16<02:17, 165kB/s]
48%|####7 | 19.9M/41.5M [03:17<02:12, 171kB/s]
48%|####7 | 19.9M/41.5M [03:17<02:08, 176kB/s]
48%|####8 | 19.9M/41.5M [03:17<02:06, 178kB/s]
48%|####8 | 20.0M/41.5M [03:17<02:05, 180kB/s]
48%|####8 | 20.0M/41.5M [03:17<02:03, 183kB/s]
48%|####8 | 20.0M/41.5M [03:17<02:02, 184kB/s]
48%|####8 | 20.0M/41.5M [03:17<02:02, 184kB/s]
48%|####8 | 20.1M/41.5M [03:18<02:01, 184kB/s]
48%|####8 | 20.1M/41.5M [03:18<02:34, 145kB/s]
49%|####8 | 20.1M/41.5M [03:18<01:53, 197kB/s]
49%|####8 | 20.2M/41.5M [03:18<01:55, 194kB/s]
49%|####8 | 20.2M/41.5M [03:18<02:06, 176kB/s]
49%|####8 | 20.2M/41.5M [03:19<02:04, 179kB/s]
49%|####8 | 20.2M/41.5M [03:19<02:03, 181kB/s]
49%|####8 | 20.3M/41.5M [03:19<02:02, 182kB/s]
49%|####8 | 20.3M/41.5M [03:19<02:01, 183kB/s]
49%|####9 | 20.4M/41.5M [03:19<02:00, 184kB/s]
49%|####9 | 20.4M/41.5M [03:19<01:51, 198kB/s]
49%|####9 | 20.4M/41.5M [03:20<01:54, 194kB/s]
49%|####9 | 20.5M/41.5M [03:20<01:47, 205kB/s]
49%|####9 | 20.5M/41.5M [03:20<01:50, 198kB/s]
49%|####9 | 20.5M/41.5M [03:20<01:45, 209kB/s]
50%|####9 | 20.6M/41.5M [03:20<01:41
, 217kB/s]
50%|####9 | 20.6M/41.5M [03:20<01:45, 208kB/s]
50%|####9 | 20.6M/41.5M [03:21<01:47, 204kB/s]
50%|####9 | 20.6M/41.5M [03:21<02:32, 144kB/s]
50%|####9 | 20.7M/41.5M [03:21<01:52, 194kB/s]
50%|####9 | 20.7M/41.5M [03:21<01:53, 191kB/s]
50%|####9 | 20.7M/41.5M [03:21<01:54, 189kB/s]
50%|##### | 20.8M/41.5M [03:22<02:42, 134kB/s]
50%|##### | 20.8M/41.5M [03:22<02:00, 180kB/s]
50%|##### | 20.8M/41.5M [03:22<02:08, 168kB/s]
50%|##### | 20.9M/41.5M [03:22<02:15, 160kB/s]
50%|##### | 20.9M/41.5M [03:22<02:20, 154kB/s]
50%|##### | 20.9M/41.5M [03:23<02:24, 149kB/s]
50%|##### | 20.9M/41.5M [03:23<02:27, 146kB/s]
51%|##### | 21.0M/41.5M [03:23<02:19, 155kB/s]
51%|##### | 21.0M/41.5M [03:23<02:25, 148kB/s]
51%|##### | 21.0M/41.5M [03:23<02:16, 158kB/s]
51%|##### | 21.0M/41.5M [03:23<02:10, 164kB/s]
51%|##### | 21.0M/41.5M [
03:24<02:54, 123kB/s]
51%|##### | 21.1M/41.5M [03:24<02:21, 152kB/s]
51%|##### | 21.1M/41.5M [03:24<02:24, 148kB/s]
51%|##### | 21.1M/41.5M [03:24<02:43, 131kB/s]
51%|##### | 21.1M/41.5M [03:24<02:40, 133kB/s]
51%|##### | 21.2M/41.5M [03:24<02:25, 146kB/s]
51%|#####1 | 21.2M/41.5M [03:25<02:17, 155kB/s]
51%|#####1 | 21.2M/41.5M [03:25<03:16, 108kB/s]
51%|#####1 | 21.2M/41.5M [03:25<02:19, 152kB/s]
51%|#####1 | 21.3M/41.5M [03:25<02:23, 148kB/s]
51%|#####1 | 21.3M/41.5M [03:25<02:26, 145kB/s]
51%|#####1 | 21.3M/41.5M [03:26<02:43, 129kB/s]
51%|#####1 | 21.3M/41.5M [03:26<02:44, 128kB/s]
51%|#####1 | 21.3M/41.5M [03:26<02:40, 131kB/s]
52%|#####1 | 21.4M/41.5M [03:26<02:22, 148kB/s]
52%|#####1 | 21.4M/41.5M [03:26<02:25, 145kB/s]
52%|#####1 | 21.4M/41.5M [03:26<02:13, 157kB/s]
52%|#####1 | 21.4M/41.5M [03:27<02:45, 127kB/s]
52%|#####1 | 21
.5M/41.5M [03:27<02:15, 155kB/s]
52%|#####1 | 21.5M/41.5M [03:27<02:19, 150kB/s]
52%|#####1 | 21.5M/41.5M [03:27<03:39, 95.5kB/s]
52%|#####1 | 21.6M/41.5M [03:27<02:21, 148kB/s]
52%|#####2 | 21.6M/41.5M [03:28<03:12, 109kB/s]
52%|#####2 | 21.6M/41.5M [03:28<02:36, 133kB/s]
52%|#####2 | 21.6M/41.5M [03:28<02:44, 126kB/s]
52%|#####2 | 21.6M/41.5M [03:28<02:56, 118kB/s]
52%|#####2 | 21.7M/41.5M [03:29<03:07, 111kB/s]
52%|#####2 | 21.7M/41.5M [03:29<03:02, 114kB/s]
52%|#####2 | 21.7M/41.5M [03:29<02:51, 121kB/s]
52%|#####2 | 21.7M/41.5M [03:29<03:04, 113kB/s]
52%|#####2 | 21.7M/41.5M [03:29<02:52, 120kB/s]
52%|#####2 | 21.8M/41.5M [03:29<03:19, 104kB/s]
52%|#####2 | 21.8M/41.5M [03:30<02:48, 123kB/s]
53%|#####2 | 21.8M/41.5M [03:30<03:02, 113kB/s]
53%|#####2 | 21.8M/41.5M [03:30<03:12, 107kB/s]
53%|#####2 | 21.8M/41.5M [03:30<03:21, 103kB/s]
53%|#
####2 | 21.9M/41.5M [03:30<03:01, 113kB/s]
53%|#####2 | 21.9M/41.5M [03:30<02:50, 121kB/s]
53%|#####2 | 21.9M/41.5M [03:31<03:03, 112kB/s]
53%|#####2 | 21.9M/41.5M [03:31<02:50, 120kB/s]
53%|#####2 | 21.9M/41.5M [03:31<02:43, 126kB/s]
53%|#####2 | 22.0M/41.5M [03:31<02:38, 129kB/s]
53%|#####2 | 22.0M/41.5M [03:31<02:52, 118kB/s]
53%|#####3 | 22.0M/41.5M [03:32<02:44, 124kB/s]
53%|#####3 | 22.0M/41.5M [03:32<02:38, 128kB/s]
53%|#####3 | 22.0M/41.5M [03:32<03:45, 90.3kB/s]
53%|#####3 | 22.1M/41.5M [03:32<02:29, 137kB/s]
53%|#####3 | 22.1M/41.5M [03:32<02:42, 125kB/s]
53%|#####3 | 22.1M/41.5M [03:33<03:18, 102kB/s]
53%|#####3 | 22.1M/41.5M [03:33<02:51, 118kB/s]
53%|#####3 | 22.2M/41.5M [03:33<03:02, 111kB/s]
53%|#####3 | 22.2M/41.5M [03:33<03:11, 106kB/s]
53%|#####3 | 22.2M/41.5M [03:33<03:18, 102kB/s]
54%|#####3 | 22.2M/41.5M [03:34<03:24, 99.0kB
/s]
54%|#####3 | 22.2M/41.5M [03:34<03:27, 97.2kB/s]
54%|#####3 | 22.2M/41.5M [03:34<03:30, 95.7kB/s]
54%|#####3 | 22.2M/41.5M [03:34<03:32, 95.2kB/s]
54%|#####3 | 22.3M/41.5M [03:34<03:18, 102kB/s]
54%|#####3 | 22.3M/41.5M [03:34<03:06, 108kB/s]
54%|#####3 | 22.3M/41.5M [03:35<04:38, 72.3kB/s]
54%|#####3 | 22.3M/41.5M [03:35<03:06, 107kB/s]
54%|#####3 | 22.3M/41.5M [03:35<03:14, 103kB/s]
54%|#####3 | 22.4M/41.5M [03:35<03:20, 100kB/s]
54%|#####3 | 22.4M/41.5M [03:35<03:24, 97.9kB/s]
54%|#####3 | 22.4M/41.5M [03:36<03:02, 109kB/s]
54%|#####4 | 22.4M/41.5M [03:36<03:11, 105kB/s]
54%|#####4 | 22.4M/41.5M [03:36<02:54, 115kB/s]
54%|#####4 | 22.5M/41.5M [03:36<04:00, 83.1kB/s]
54%|#####4 | 22.5M/41.5M [03:36<03:04, 108kB/s]
54%|#####4 | 22.5M/41.5M [03:37<03:11, 104kB/s]
54%|#####4 | 22.5M/41.5M [03:37<03:17, 101kB/s]
54%|#####4 | 22.5M/41.5
M [03:37<03:21, 98.4kB/s]
54%|#####4 | 22.6M/41.5M [03:37<03:00, 110kB/s]
54%|#####4 | 22.6M/41.5M [03:37<03:09, 105kB/s]
54%|#####4 | 22.6M/41.5M [03:38<02:52, 115kB/s]
54%|#####4 | 22.6M/41.5M [03:38<03:03, 108kB/s]
55%|#####4 | 22.6M/41.5M [03:38<03:11, 103kB/s]
55%|#####4 | 22.6M/41.5M [03:38<02:53, 114kB/s]
55%|#####4 | 22.7M/41.5M [03:38<03:03, 107kB/s]
55%|#####4 | 22.7M/41.5M [03:38<02:49, 117kB/s]
55%|#####4 | 22.7M/41.5M [03:39<02:39, 123kB/s]
55%|#####4 | 22.7M/41.5M [03:39<02:33, 128kB/s]
55%|#####4 | 22.8M/41.5M [03:39<02:47, 117kB/s]
55%|#####4 | 22.8M/41.5M [03:39<02:22, 137kB/s]
55%|#####4 | 22.8M/41.5M [03:40<03:36, 90.4kB/s]
55%|#####5 | 22.8M/41.5M [03:40<03:01, 108kB/s]
55%|#####5 | 22.9M/41.5M [03:40<02:36, 124kB/s]
55%|#####5 | 22.9M/41.5M [03:40<02:46, 117kB/s]
55%|#####5 | 22.9M/41.5M [03:40<02:56, 111kB/s]
55%|#####5
| 22.9M/41.5M [03:41<03:15, 99.7kB/s]
55%|#####5 | 22.9M/41.5M [03:41<03:19, 97.6kB/s]
55%|#####5 | 23.0M/41.5M [03:41<03:21, 96.3kB/s]
55%|#####5 | 23.0M/41.5M [03:41<03:24, 95.2kB/s]
55%|#####5 | 23.0M/41.5M [03:41<03:25, 94.3kB/s]
55%|#####5 | 23.0M/41.5M [03:41<03:13, 100kB/s]
55%|#####5 | 23.0M/41.5M [03:42<03:17, 97.9kB/s]
56%|#####5 | 23.0M/41.5M [03:42<03:21, 96.2kB/s]
56%|#####5 | 23.0M/41.5M [03:42<03:07, 103kB/s]
56%|#####5 | 23.1M/41.5M [03:42<03:02, 106kB/s]
56%|#####5 | 23.1M/41.5M [03:42<03:23, 95.0kB/s]
56%|#####5 | 23.1M/41.5M [03:43<02:59, 107kB/s]
56%|#####5 | 23.1M/41.5M [03:43<03:06, 103kB/s]
56%|#####5 | 23.1M/41.5M [03:43<03:12, 99.9kB/s]
56%|#####5 | 23.2M/41.5M [03:43<03:30, 91.4kB/s]
56%|#####5 | 23.2M/41.5M [03:43<02:51, 112kB/s]
56%|#####5 | 23.2M/41.5M [03:44<04:50, 66.0kB/s]
56%|#####5 | 23.2M/41.5M [03:44<03:41,
86.3kB/s]
56%|#####6 | 23.2M/41.5M [03:44<03:52, 82.2kB/s]
56%|#####6 | 23.3M/41.5M [03:44<03:46, 84.5kB/s]
56%|#####6 | 23.3M/41.5M [03:45<04:05, 77.9kB/s]
56%|#####6 | 23.3M/41.5M [03:45<03:54, 81.4kB/s]
56%|#####6 | 23.3M/41.5M [03:45<03:46, 84.1kB/s]
56%|#####6 | 23.3M/41.5M [03:45<03:56, 80.7kB/s]
56%|#####6 | 23.3M/41.5M [03:45<03:47, 83.7kB/s]
56%|#####6 | 23.4M/41.5M [03:46<05:26, 58.2kB/s]
56%|#####6 | 23.4M/41.5M [03:46<03:44, 84.7kB/s]
56%|#####6 | 23.4M/41.5M [03:46<03:51, 81.9kB/s]
56%|#####6 | 23.4M/41.5M [03:47<03:44, 84.4kB/s]
56%|#####6 | 23.4M/41.5M [03:47<03:39, 86.4kB/s]
57%|#####6 | 23.4M/41.5M [03:47<03:35, 88.0kB/s]
57%|#####6 | 23.5M/41.5M [03:47<03:32, 89.1kB/s]
57%|#####6 | 23.5M/41.5M [03:47<03:15, 96.5kB/s]
57%|#####6 | 23.5M/41.5M [03:47<03:18, 95.2kB/s]
57%|#####6 | 23.5M/41.5M [03:48<03:19, 94.3kB/s]
57%|#####6
| 23.5M/41.5M [03:48<04:37, 67.8kB/s]
57%|#####6 | 23.6M/41.5M [03:48<03:15, 96.0kB/s]
57%|#####6 | 23.6M/41.5M [03:48<03:30, 89.3kB/s]
57%|#####6 | 23.6M/41.5M [03:49<03:28, 90.1kB/s]
57%|#####6 | 23.6M/41.5M [03:49<03:26, 90.7kB/s]
57%|#####6 | 23.6M/41.5M [03:49<03:25, 91.0kB/s]
57%|#####6 | 23.6M/41.5M [03:49<03:10, 98.5kB/s]
57%|#####6 | 23.6M/41.5M [03:49<03:13, 96.6kB/s]
57%|#####7 | 23.7M/41.5M [03:50<04:30, 69.0kB/s]
57%|#####7 | 23.7M/41.5M [03:50<03:36, 86.2kB/s]
57%|#####7 | 23.7M/41.5M [03:50<03:32, 87.6kB/s]
57%|#####7 | 23.7M/41.5M [03:50<03:29, 88.8kB/s]
57%|#####7 | 23.7M/41.5M [03:50<03:27, 89.7kB/s]
57%|#####7 | 23.8M/41.5M [03:51<03:25, 90.4kB/s]
57%|#####7 | 23.8M/41.5M [03:51<03:24, 90.9kB/s]
57%|#####7 | 23.8M/41.5M [03:51<04:21, 70.9kB/s]
57%|#####7 | 23.8M/41.5M [03:51<04:23, 70.3kB/s]
57%|#####7 | 23.8M/41.5M [03:52<03:37
, 85.0kB/s]
57%|#####7 | 23.9M/41.5M [03:52<04:23, 70.1kB/s]
58%|#####7 | 23.9M/41.5M [03:52<04:19, 71.1kB/s]
58%|#####7 | 23.9M/41.5M [03:52<04:26, 69.3kB/s]
58%|#####7 | 23.9M/41.5M [03:53<04:51, 63.4kB/s]
58%|#####7 | 23.9M/41.5M [03:53<04:19, 71.1kB/s]
58%|#####7 | 23.9M/41.5M [03:53<04:15, 72.0kB/s]
58%|#####7 | 23.9M/41.5M [03:53<04:24, 69.7kB/s]
58%|#####7 | 23.9M/41.5M [03:53<04:01, 76.2kB/s]
58%|#####7 | 24.0M/41.5M [03:53<03:47, 81.0kB/s]
58%|#####7 | 24.0M/41.5M [03:54<03:37, 84.3kB/s]
58%|#####7 | 24.0M/41.5M [03:54<03:31, 86.7kB/s]
58%|#####7 | 24.0M/41.5M [03:54<03:27, 88.3kB/s]
58%|#####7 | 24.0M/41.5M [03:54<03:24, 89.5kB/s]
58%|#####7 | 24.0M/41.5M [03:54<02:55, 104kB/s]
58%|#####7 | 24.1M/41.5M [03:54<03:01, 101kB/s]
58%|#####8 | 24.1M/41.5M [03:55<02:43, 112kB/s]
58%|#####8 | 24.1M/41.5M [03:55<02:16, 134kB/s]
58%|#####8
| 24.1M/41.5M [03:55<02:14, 135kB/s]
58%|#####8 | 24.2M/41.5M [03:55<01:50, 164kB/s]
58%|#####8 | 24.2M/41.5M [03:55<01:46, 170kB/s]
58%|#####8 | 24.2M/41.5M [03:56<01:36, 188kB/s]
59%|#####8 | 24.3M/41.5M [03:56<01:24, 215kB/s]
59%|#####8 | 24.3M/41.5M [03:56<01:17, 233kB/s]
59%|#####8 | 24.4M/41.5M [03:56<01:27, 204kB/s]
59%|#####8 | 24.4M/41.5M [03:56<01:19, 226kB/s]
59%|#####8 | 24.5M/41.5M [03:56<01:06, 269kB/s]
59%|#####9 | 24.5M/41.5M [03:57<01:35, 187kB/s]
59%|#####9 | 24.6M/41.5M [03:57<01:06, 266kB/s]
59%|#####9 | 24.6M/41.5M [03:57<01:12, 245kB/s]
59%|#####9 | 24.6M/41.5M [03:57<01:17, 229kB/s]
59%|#####9 | 24.7M/41.5M [03:58<01:26, 203kB/s]
60%|#####9 | 24.7M/41.5M [03:58<01:23, 211kB/s]
60%|#####9 | 24.7M/41.5M [03:58<01:32, 190kB/s]
60%|#####9 | 24.8M/41.5M [03:58<01:38, 178kB/s]
60%|#####9 | 24.8M/41.5M [03:58<02:19, 126kB/s]
60%
|#####9 | 24.8M/41.5M [03:59<02:05, 140kB/s]
60%|#####9 | 24.9M/41.5M [03:59<01:49, 160kB/s]
60%|###### | 24.9M/41.5M [03:59<01:59, 146kB/s]
60%|###### | 24.9M/41.5M [03:59<02:10, 133kB/s]
60%|###### | 24.9M/41.5M [04:00<02:21, 123kB/s]
60%|###### | 24.9M/41.5M [04:00<02:31, 114kB/s]
60%|###### | 25.0M/41.5M [04:00<02:29, 116kB/s]
60%|###### | 25.0M/41.5M [04:00<02:38, 109kB/s]
60%|###### | 25.0M/41.5M [04:00<02:26, 118kB/s]
60%|###### | 25.0M/41.5M [04:00<02:36, 110kB/s]
60%|###### | 25.0M/41.5M [04:01<02:25, 119kB/s]
60%|###### | 25.1M/41.5M [04:01<02:58, 96.6kB/s]
60%|###### | 25.1M/41.5M [04:01<03:37, 79.0kB/s]
61%|###### | 25.1M/41.5M [04:01<02:34, 111kB/s]
61%|###### | 25.1M/41.5M [04:02<03:03, 93.8kB/s]
61%|###### | 25.1M/41.5M [04:02<02:52, 99.5kB/s]
61%|###### | 25.1M/41.5M [04:02<02:55, 97.5kB/s]
61%|###### | 25.2M/41.5M [04:02<03:10,
89.9kB/s]
61%|###### | 25.2M/41.5M [04:02<03:09, 90.5kB/s]
61%|###### | 25.2M/41.5M [04:03<04:41, 60.7kB/s]
61%|###### | 25.2M/41.5M [04:03<03:26, 82.8kB/s]
61%|###### | 25.2M/41.5M [04:03<03:20, 84.9kB/s]
61%|###### | 25.3M/41.5M [04:03<03:16, 86.7kB/s]
61%|###### | 25.3M/41.5M [04:03<03:13, 88.0kB/s]
61%|###### | 25.3M/41.5M [04:04<03:10, 89.3kB/s]
61%|###### | 25.3M/41.5M [04:04<03:08, 90.1kB/s]
61%|######1 | 25.3M/41.5M [04:04<04:53, 57.8kB/s]
61%|######1 | 25.3M/41.5M [04:05<04:34, 61.6kB/s]
61%|######1 | 25.4M/41.5M [04:05<03:40, 76.6kB/s]
61%|######1 | 25.4M/41.5M [04:05<04:28, 62.9kB/s]
61%|######1 | 25.4M/41.5M [04:05<04:29, 62.6kB/s]
61%|######1 | 25.4M/41.5M [04:06<05:52, 47.9kB/s]
61%|######1 | 25.4M/41.5M [04:06<04:54, 57.2kB/s]
61%|######1 | 25.4M/41.5M [04:06<05:08, 54.7kB/s]
61%|######1 | 25.4M/41.5M [04:06<04:23, 63.9kB/s]
61%|######1
| 25.4M/41.5M [04:06<04:43, 59.4kB/s]
61%|######1 | 25.5M/41.5M [04:07<05:01, 55.8kB/s]
61%|######1 | 25.5M/41.5M [04:07<05:16, 53.1kB/s]
61%|######1 | 25.5M/41.5M [04:07<04:21, 64.1kB/s]
61%|######1 | 25.5M/41.5M [04:07<04:44, 59.0kB/s]
61%|######1 | 25.5M/41.5M [04:07<04:04, 68.6kB/s]
61%|######1 | 25.5M/41.5M [04:08<04:29, 62.1kB/s]
61%|######1 | 25.5M/41.5M [04:08<06:19, 44.1kB/s]
62%|######1 | 25.5M/41.5M [04:08<06:10, 45.1kB/s]
62%|######1 | 25.6M/41.5M [04:09<06:06, 45.5kB/s]
62%|######1 | 25.6M/41.5M [04:09<04:34, 60.8kB/s]
62%|######1 | 25.6M/41.5M [04:09<04:47, 58.0kB/s]
62%|######1 | 25.6M/41.5M [04:10<05:00, 55.5kB/s]
62%|######1 | 25.6M/41.5M [04:10<05:12, 53.3kB/s]
62%|######1 | 25.6M/41.5M [04:10<05:23, 51.5kB/s]
62%|######1 | 25.6M/41.5M [04:10<05:32, 50.1kB/s]
62%|######1 | 25.6M/41.5M [04:10<04:29, 61.6kB/s]
62%|######1 | 25.6M/41.5M [04:10<04:50,
57.3kB/s]
62%|######1 | 25.7M/41.5M [04:11<05:06, 54.1kB/s]
62%|######1 | 25.7M/41.5M [04:11<06:53, 40.1kB/s]
62%|######1 | 25.7M/41.5M [04:11<04:18, 64.0kB/s]
62%|######1 | 25.7M/41.5M [04:11<03:52, 71.3kB/s]
62%|######1 | 25.7M/41.5M [04:11<04:16, 64.5kB/s]
62%|######2 | 25.7M/41.5M [04:12<03:48, 72.2kB/s]
62%|######2 | 25.7M/41.5M [04:12<03:31, 77.9kB/s]
62%|######2 | 25.8M/41.5M [04:12<04:00, 68.7kB/s]
62%|######2 | 25.8M/41.5M [04:12<03:38, 75.6kB/s]
62%|######2 | 25.8M/41.5M [04:12<03:24, 80.5kB/s]
62%|######2 | 25.8M/41.5M [04:13<03:15, 84.0kB/s]
62%|######2 | 25.8M/41.5M [04:13<03:10, 86.4kB/s]
62%|######2 | 25.8M/41.5M [04:13<03:06, 88.1kB/s]
62%|######2 | 25.8M/41.5M [04:13<03:03, 89.4kB/s]
62%|######2 | 25.9M/41.5M [04:13<03:01, 90.3kB/s]
62%|######2 | 25.9M/41.5M [04:13<03:00, 90.9kB/s]
62%|######2 | 25.9M/41.5M [04:14<02:59, 91.3kB/s]
62%|######2
| 25.9M/41.5M [04:14<02:35, 105kB/s]
62%|######2 | 25.9M/41.5M [04:14<02:40, 101kB/s]
63%|######2 | 26.0M/41.5M [04:14<02:24, 112kB/s]
63%|######2 | 26.0M/41.5M [04:14<02:32, 106kB/s]
63%|######2 | 26.0M/41.5M [04:14<02:20, 116kB/s]
63%|######2 | 26.0M/41.5M [04:15<02:12, 123kB/s]
63%|######2 | 26.0M/41.5M [04:15<02:07, 127kB/s]
63%|######2 | 26.1M/41.5M [04:15<02:03, 131kB/s]
63%|######2 | 26.1M/41.5M [04:15<02:01, 133kB/s]
63%|######2 | 26.1M/41.5M [04:15<01:59, 135kB/s]
63%|######2 | 26.1M/41.5M [04:16<01:58, 136kB/s]
63%|######3 | 26.2M/41.5M [04:16<02:19, 115kB/s]
63%|######3 | 26.2M/41.5M [04:16<02:31, 106kB/s]
63%|######3 | 26.2M/41.5M [04:16<01:51, 144kB/s]
63%|######3 | 26.3M/41.5M [04:17<02:30, 106kB/s]
63%|######3 | 26.3M/41.5M [04:17<02:37, 101kB/s]
63%|######3 | 26.3M/41.5M [04:17<02:40, 99.2kB/s]
63%|######3 | 26.3M/41.5M [04:18<02:27, 108kB/s]
63%|######3 | 26.3M/41.5M [04:18<02:32, 104kB/s]
64%|######3 | 26.4M/41.5M [04:18<02:36, 101kB/s]
64%|######3 | 26.4M/41.5M [04:18<02:40, 98.7kB/s]
64%|######3 | 26.4M/41.5M [04:18<03:05, 85.4kB/s]
64%|######3 | 26.4M/41.5M [04:19<03:25, 76.9kB/s]
64%|######3 | 26.4M/41.5M [04:19<06:35, 39.9kB/s]
64%|######3 | 26.5M/41.5M [04:20<03:12, 81.8kB/s]
64%|######3 | 26.5M/41.5M [04:20<02:51, 91.7kB/s]
64%|######3 | 26.5M/41.5M [04:20<02:35, 101kB/s]
64%|######3 | 26.5M/41.5M [04:20<02:23, 109kB/s]
64%|######4 | 26.6M/41.5M [04:20<02:14, 116kB/s]
64%|######4 | 26.6M/41.5M [04:21<02:40, 97.1kB/s]
64%|######4 | 26.6M/41.5M [04:21<01:53, 138kB/s]
64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
64%|######4 | 26.7M/41.5M [04:22<01:52, 138kB/s]
64%|######4 | 26.8M/41.5M [04:22
<02:23, 107kB/s]
65%|######4 | 26.8M/41.5M [04:22<01:43, 148kB/s]
65%|######4 | 26.8M/41.5M [04:22<01:45, 146kB/s]
65%|######4 | 26.8M/41.5M [04:23<02:28, 104kB/s]
65%|######4 | 26.9M/41.5M [04:23<01:46, 144kB/s]
65%|######4 | 26.9M/41.5M [04:23<01:47, 142kB/s]
65%|######4 | 26.9M/41.5M [04:23<02:29, 102kB/s]
65%|######4 | 26.9M/41.5M [04:24<02:32, 100kB/s]
65%|######5 | 27.0M/41.5M [04:24<02:05, 121kB/s]
65%|######5 | 27.0M/41.5M [04:24<02:14, 113kB/s]
65%|######5 | 27.0M/41.5M [04:24<02:20, 108kB/s]
65%|######5 | 27.0M/41.5M [04:24<02:10, 116kB/s]
65%|######5 | 27.0M/41.5M [04:24<02:18, 109kB/s]
65%|######5 | 27.1M/41.5M [04:25<02:08, 118kB/s]
65%|######5 | 27.1M/41.5M [04:25<02:01, 124kB/s]
65%|######5 | 27.1M/41.5M [04:25<02:11, 115kB/s]
65%|######5 | 27.1M/41.5M [04:25<02:03, 122kB/s]
65%|######5 | 27.2M/41.5M [04:25<01:58, 127kB/s]
65%|######5 | 27.2M/4
1.5M [04:26<02:47, 89.5kB/s]
66%|######5 | 27.2M/41.5M [04:26<02:00, 124kB/s]
66%|######5 | 27.2M/41.5M [04:26<02:08, 116kB/s]
66%|######5 | 27.2M/41.5M [04:26<02:16, 110kB/s]
66%|######5 | 27.3M/41.5M [04:26<02:06, 118kB/s]
66%|######5 | 27.3M/41.5M [04:27<02:14, 110kB/s]
66%|######5 | 27.3M/41.5M [04:27<02:05, 118kB/s]
66%|######5 | 27.3M/41.5M [04:27<01:59, 124kB/s]
66%|######5 | 27.4M/41.5M [04:27<01:55, 128kB/s]
66%|######5 | 27.4M/41.5M [04:27<01:52, 131kB/s]
66%|######6 | 27.4M/41.5M [04:27<02:03, 120kB/s]
66%|######6 | 27.4M/41.5M [04:28<01:57, 125kB/s]
66%|######6 | 27.4M/41.5M [04:28<01:54, 129kB/s]
66%|######6 | 27.5M/41.5M [04:28<01:51, 132kB/s]
66%|######6 | 27.5M/41.5M [04:28<01:49, 134kB/s]
66%|######6 | 27.5M/41.5M [04:28<01:48, 135kB/s]
66%|######6 | 27.5M/41.5M [04:29<01:47, 136kB/s]
66%|######6 | 27.6M/41.5M [04:29<01:36, 151kB/s]
66%|######
6 | 27.6M/41.5M [04:29<01:39, 147kB/s]
67%|######6 | 27.6M/41.5M [04:29<01:40, 144kB/s]
67%|######6 | 27.6M/41.5M [04:29<01:32, 156kB/s]
67%|######6 | 27.7M/41.5M [04:29<01:27, 165kB/s]
67%|######6 | 27.7M/41.5M [04:30<01:59, 121kB/s]
67%|######6 | 27.8M/41.5M [04:30<01:55, 124kB/s]
67%|######6 | 27.8M/41.5M [04:30<01:33, 154kB/s]
67%|######7 | 27.8M/41.5M [04:31<01:41, 142kB/s]
67%|######7 | 27.8M/41.5M [04:31<01:50, 130kB/s]
67%|######7 | 27.8M/41.5M [04:31<01:51, 128kB/s]
67%|######7 | 27.9M/41.5M [04:31<02:00, 118kB/s]
67%|######7 | 27.9M/41.5M [04:31<01:59, 120kB/s]
67%|######7 | 27.9M/41.5M [04:31<01:58, 121kB/s]
67%|######7 | 27.9M/41.5M [04:32<02:07, 112kB/s]
67%|######7 | 27.9M/41.5M [04:32<02:04, 114kB/s]
67%|######7 | 27.9M/41.5M [04:32<02:02, 116kB/s]
67%|######7 | 28.0M/41.5M [04:32<01:59, 119kB/s]
67%|######7 | 28.0M/41.5M [04:32<01:58, 120kB/s]
67%|######7 | 28.0M/41.5M [04:32<02:42, 87.0kB/s]
68%|######7 | 28.0M/41.5M [04:33<01:54, 123kB/s]
68%|######7 | 28.0M/41.5M [04:33<02:04, 114kB/s]
68%|######7 | 28.0M/41.5M [04:33<02:51, 82.3kB/s]
68%|######7 | 28.1M/41.5M [04:33<02:20, 100kB/s]
68%|######7 | 28.1M/41.5M [04:33<02:29, 94.0kB/s]
68%|######7 | 28.1M/41.5M [04:34<02:30, 93.5kB/s]
68%|######7 | 28.1M/41.5M [04:34<02:30, 93.0kB/s]
68%|######7 | 28.1M/41.5M [04:34<02:30, 92.8kB/s]
68%|######7 | 28.2M/41.5M [04:34<03:13, 72.2kB/s]
68%|######7 | 28.2M/41.5M [04:35<02:38, 88.0kB/s]
68%|######7 | 28.2M/41.5M [04:35<02:51, 81.3kB/s]
68%|######7 | 28.2M/41.5M [04:35<02:45, 84.0kB/s]
68%|######8 | 28.2M/41.5M [04:35<02:41, 86.2kB/s]
68%|######8 | 28.2M/41.5M [04:35<02:38, 87.8kB/s]
68%|######8 | 28.3M/41.5M [04:36<02:35, 89.1kB/s]
68%|######8 | 28.3M/41.5M [04:36<02:34, 90.0kB/s]
68%|######8 | 28.3M/41.5M
[04:36<02:51, 80.7kB/s]
68%|######8 | 28.3M/41.5M [04:36<02:44, 83.8kB/s]
68%|######8 | 28.3M/41.5M [04:36<02:21, 97.7kB/s]
68%|######8 | 28.3M/41.5M [04:36<02:23, 96.1kB/s]
68%|######8 | 28.4M/41.5M [04:37<02:19, 98.8kB/s]
68%|######8 | 28.4M/41.5M [04:37<02:22, 96.7kB/s]
68%|######8 | 28.4M/41.5M [04:37<02:12, 103kB/s]
68%|######8 | 28.4M/41.5M [04:37<02:08, 106kB/s]
68%|######8 | 28.4M/41.5M [04:37<01:55, 118kB/s]
69%|######8 | 28.4M/41.5M [04:37<01:59, 114kB/s]
69%|######8 | 28.4M/41.5M [04:37<01:56, 117kB/s]
69%|######8 | 28.5M/41.5M [04:38<01:50, 124kB/s]
69%|######8 | 28.5M/41.5M [04:38<01:49, 124kB/s]
69%|######8 | 28.5M/41.5M [04:38<02:45, 82.3kB/s]
69%|######8 | 28.5M/41.5M [04:38<02:29, 91.0kB/s]
69%|######8 | 28.5M/41.5M [04:38<01:44, 130kB/s]
69%|######8 | 28.6M/41.5M [04:39<02:29, 90.9kB/s]
69%|######8 | 28.6M/41.5M [04:39<02:03, 110kB/s]
69%|#
#####8 | 28.6M/41.5M [04:39<02:08, 105kB/s]
69%|######8 | 28.6M/41.5M [04:39<02:39, 84.8kB/s]
69%|######9 | 28.6M/41.5M [04:39<02:35, 86.7kB/s]
69%|######9 | 28.6M/41.5M [04:40<02:41, 83.5kB/s]
69%|######9 | 28.7M/41.5M [04:40<02:36, 85.8kB/s]
69%|######9 | 28.7M/41.5M [04:40<02:24, 93.0kB/s]
69%|######9 | 28.7M/41.5M [04:40<02:24, 92.8kB/s]
69%|######9 | 28.7M/41.5M [04:40<02:24, 92.6kB/s]
69%|######9 | 28.7M/41.5M [04:41<02:13, 99.8kB/s]
69%|######9 | 28.8M/41.5M [04:41<02:08, 104kB/s]
69%|######9 | 28.8M/41.5M [04:41<02:04, 107kB/s]
69%|######9 | 28.8M/41.5M [04:41<02:01, 110kB/s]
69%|######9 | 28.8M/41.5M [04:41<01:59, 111kB/s]
70%|######9 | 28.8M/41.5M [04:41<01:51, 119kB/s]
70%|######9 | 28.9M/41.5M [04:42<01:46, 125kB/s]
70%|######9 | 28.9M/41.5M [04:42<01:47, 123kB/s]
70%|######9 | 28.9M/41.5M [04:42<01:43, 128kB/s]
70%|######9 | 28.9M/41.5M [04:42<02:18,
95.3kB/s]
70%|######9 | 29.0M/41.5M [04:43<01:34, 139kB/s]
70%|######9 | 29.0M/41.5M [04:43<01:43, 127kB/s]
70%|######9 | 29.0M/41.5M [04:43<01:40, 130kB/s]
70%|######9 | 29.0M/41.5M [04:43<01:38, 132kB/s]
70%|####### | 29.0M/41.5M [04:43<01:50, 118kB/s]
70%|####### | 29.1M/41.5M [04:43<01:42, 127kB/s]
70%|####### | 29.1M/41.5M [04:44<02:19, 93.4kB/s]
70%|####### | 29.1M/41.5M [04:44<01:46, 122kB/s]
70%|####### | 29.1M/41.5M [04:44<01:53, 114kB/s]
70%|####### | 29.2M/41.5M [04:44<01:59, 108kB/s]
70%|####### | 29.2M/41.5M [04:45<02:36, 82.6kB/s]
70%|####### | 29.2M/41.5M [04:45<03:08, 68.3kB/s]
70%|####### | 29.2M/41.5M [04:45<02:34, 83.5kB/s]
70%|####### | 29.2M/41.5M [04:46<03:05, 69.2kB/s]
70%|####### | 29.2M/41.5M [04:46<02:53, 74.2kB/s]
71%|####### | 29.3M/41.5M [04:46<02:46, 77.0kB/s]
71%|####### | 29.3M/41.5M [04:46<03:57, 54.0kB/s]
71%|####### | 29.
3M/41.5M [04:47<04:45, 44.8kB/s]
71%|####### | 29.3M/41.5M [04:48<04:41, 45.3kB/s]
71%|####### | 29.3M/41.5M [04:48<03:34, 59.4kB/s]
71%|####### | 29.3M/41.5M [04:48<03:43, 57.0kB/s]
71%|####### | 29.4M/41.5M [04:48<05:29, 38.6kB/s]
71%|####### | 29.4M/41.5M [04:49<04:23, 48.3kB/s]
71%|####### | 29.4M/41.5M [04:49<06:09, 34.4kB/s]
71%|####### | 29.4M/41.5M [04:49<05:36, 37.7kB/s]
71%|####### | 29.4M/41.5M [04:50<05:23, 39.2kB/s]
71%|####### | 29.4M/41.5M [04:50<05:12, 40.5kB/s]
71%|####### | 29.4M/41.5M [04:50<05:03, 41.8kB/s]
71%|####### | 29.4M/41.5M [04:50<04:55, 42.8kB/s]
71%|####### | 29.4M/41.5M [04:50<04:49, 43.6kB/s]
71%|####### | 29.4M/41.5M [04:51<04:45, 44.3kB/s]
71%|####### | 29.4M/41.5M [04:51<04:41, 44.8kB/s]
71%|####### | 29.5M/41.5M [04:51<04:39, 45.2kB/s]
71%|#######1 | 29.5M/41.5M [04:51<04:37, 45.5kB/s]
71%|#######1 | 29.5M/41.5M [04:51<03:33, 59.1k
B/s]
71%|#######1 | 29.5M/41.5M [04:51<03:47, 55.3kB/s]
71%|#######1 | 29.5M/41.5M [04:52<03:09, 66.2kB/s]
71%|#######1 | 29.5M/41.5M [04:52<02:49, 73.9kB/s]
71%|#######1 | 29.5M/41.5M [04:52<03:11, 65.7kB/s]
71%|#######1 | 29.5M/41.5M [04:52<02:50, 73.6kB/s]
71%|#######1 | 29.6M/41.5M [04:52<02:38, 79.2kB/s]
71%|#######1 | 29.6M/41.5M [04:52<02:08, 96.9kB/s]
71%|#######1 | 29.6M/41.5M [04:53<01:54, 109kB/s]
71%|#######1 | 29.6M/41.5M [04:53<01:45, 118kB/s]
71%|#######1 | 29.6M/41.5M [04:53<01:40, 124kB/s]
72%|#######1 | 29.7M/41.5M [04:53<01:27, 142kB/s]
72%|#######1 | 29.7M/41.5M [04:53<01:13, 169kB/s]
72%|#######1 | 29.8M/41.5M [04:54<01:05, 187kB/s]
72%|#######1 | 29.8M/41.5M [04:54<00:57, 214kB/s]
72%|#######1 | 29.9M/41.5M [04:54<00:49, 247kB/s]
72%|#######2 | 29.9M/41.5M [04:54<00:53, 227kB/s]
72%|#######2 | 30.0M/41.5M [04:54<00:42, 284kB/s]
72%|#######2 | 30.0M/41.5M
[04:54<00:44, 268kB/s]
72%|#######2 | 30.0M/41.5M [04:55<00:44, 271kB/s]
73%|#######2 | 30.1M/41.5M [04:55<00:43, 272kB/s]
73%|#######2 | 30.1M/41.5M [04:55<00:41, 288kB/s]
73%|#######2 | 30.2M/41.5M [04:55<00:41, 284kB/s]
73%|#######2 | 30.2M/41.5M [04:55<00:46, 254kB/s]
73%|#######3 | 30.3M/41.5M [04:55<00:40, 288kB/s]
73%|#######3 | 30.3M/41.5M [04:56<00:59, 198kB/s]
73%|#######3 | 30.4M/41.5M [04:56<00:44, 263kB/s]
73%|#######3 | 30.4M/41.5M [04:56<00:47, 242kB/s]
73%|#######3 | 30.5M/41.5M [04:56<00:51, 227kB/s]
73%|#######3 | 30.5M/41.5M [04:57<00:53, 215kB/s]
74%|#######3 | 30.5M/41.5M [04:57<01:16, 150kB/s]
74%|#######3 | 30.6M/41.5M [04:57<00:53, 214kB/s]
74%|#######3 | 30.6M/41.5M [04:57<00:55, 206kB/s]
74%|#######3 | 30.6M/41.5M [04:57<01:00, 188kB/s]
74%|#######3 | 30.7M/41.5M [04:58<01:05, 174kB/s]
74%|#######3 | 30.7M/41.5M [04:58<01:03, 177kB/s]
74%|#######4 |
30.7M/41.5M [04:58<01:27, 129kB/s]
74%|#######4 | 30.8M/41.5M [04:58<01:00, 187kB/s]
74%|#######4 | 30.8M/41.5M [04:59<01:04, 174kB/s]
74%|#######4 | 30.8M/41.5M [04:59<01:07, 165kB/s]
74%|#######4 | 30.9M/41.5M [04:59<01:10, 157kB/s]
74%|#######4 | 30.9M/41.5M [04:59<01:13, 152kB/s]
74%|#######4 | 30.9M/41.5M [04:59<01:08, 161kB/s]
75%|#######4 | 30.9M/41.5M [04:59<01:11, 155kB/s]
75%|#######4 | 31.0M/41.5M [05:00<01:07, 163kB/s]
75%|#######4 | 31.0M/41.5M [05:00<01:10, 156kB/s]
75%|#######4 | 31.0M/41.5M [05:00<01:12, 151kB/s]
75%|#######4 | 31.0M/41.5M [05:00<01:08, 161kB/s]
75%|#######4 | 31.1M/41.5M [05:01<01:47, 102kB/s]
75%|#######5 | 31.1M/41.5M [05:01<00:58, 187kB/s]
75%|#######5 | 31.2M/41.5M [05:01<01:29, 122kB/s]
75%|#######5 | 31.2M/41.5M [05:01<01:10, 152kB/s]
75%|#######5 | 31.2M/41.5M [05:02<01:12, 149kB/s]
75%|#######5 | 31.2M/41.5M [05:02<01:30, 118kB/s]
75%|#
######5 | 31.3M/41.5M [05:02<02:16, 78.5kB/s]
75%|#######5 | 31.3M/41.5M [05:03<02:21, 75.7kB/s]
76%|#######5 | 31.4M/41.5M [05:04<02:07, 83.3kB/s]
76%|#######5 | 31.4M/41.5M [05:04<01:30, 117kB/s]
76%|#######5 | 31.4M/41.5M [05:04<01:42, 103kB/s]
76%|#######5 | 31.4M/41.5M [05:04<01:43, 102kB/s]
76%|#######5 | 31.5M/41.5M [05:05<02:29, 70.4kB/s]
76%|#######5 | 31.5M/41.5M [05:05<01:55, 91.0kB/s]
76%|#######5 | 31.5M/41.5M [05:05<02:39, 65.8kB/s]
76%|#######5 | 31.5M/41.5M [05:06<02:14, 77.9kB/s]
76%|#######6 | 31.5M/41.5M [05:06<02:09, 80.5kB/s]
76%|#######6 | 31.6M/41.5M [05:06<02:32, 68.4kB/s]
76%|#######6 | 31.6M/41.5M [05:06<02:21, 73.3kB/s]
76%|#######6 | 31.6M/41.5M [05:07<02:14, 77.4kB/s]
76%|#######6 | 31.6M/41.5M [05:07<02:07, 81.0kB/s]
76%|#######6 | 31.6M/41.5M [05:07<02:34, 66.8kB/s]
76%|#######6 | 31.6M/41.5M [05:07<02:22, 72.6kB/s]
76%|#######6 | 31.7M/41.5M [05:07<
02:13, 77.4kB/s]
76%|#######6 | 31.7M/41.5M [05:08<02:06, 81.2kB/s]
76%|#######6 | 31.7M/41.5M [05:08<02:02, 84.2kB/s]
76%|#######6 | 31.7M/41.5M [05:08<01:43, 99.2kB/s]
76%|#######6 | 31.7M/41.5M [05:08<01:45, 97.3kB/s]
77%|#######6 | 31.7M/41.5M [05:08<01:46, 95.8kB/s]
77%|#######6 | 31.8M/41.5M [05:08<01:47, 94.8kB/s]
77%|#######6 | 31.8M/41.5M [05:09<01:48, 94.1kB/s]
77%|#######6 | 31.8M/41.5M [05:09<01:34, 107kB/s]
77%|#######6 | 31.8M/41.5M [05:09<01:38, 103kB/s]
77%|#######6 | 31.8M/41.5M [05:09<01:29, 113kB/s]
77%|#######6 | 31.9M/41.5M [05:09<01:34, 107kB/s]
77%|#######6 | 31.9M/41.5M [05:10<01:38, 103kB/s]
77%|#######6 | 31.9M/41.5M [05:10<01:28, 113kB/s]
77%|#######6 | 31.9M/41.5M [05:10<01:33, 107kB/s]
77%|#######6 | 31.9M/41.5M [05:10<01:37, 103kB/s]
77%|#######6 | 31.9M/41.5M [05:10<01:40, 99.4kB/s]
77%|#######7 | 32.0M/41.5M [05:10<01:42, 97.3kB/s]
77%|#######7
| 32.0M/41.5M [05:11<01:44, 95.8kB/s]
77%|#######7 | 32.0M/41.5M [05:11<01:45, 94.7kB/s]
77%|#######7 | 32.0M/41.5M [05:11<01:32, 108kB/s]
77%|#######7 | 32.0M/41.5M [05:11<01:36, 103kB/s]
77%|#######7 | 32.0M/41.5M [05:11<01:39, 99.9kB/s]
77%|#######7 | 32.1M/41.5M [05:11<01:28, 111kB/s]
77%|#######7 | 32.1M/41.5M [05:12<01:33, 106kB/s]
77%|#######7 | 32.1M/41.5M [05:12<01:25, 115kB/s]
77%|#######7 | 32.1M/41.5M [05:12<01:30, 109kB/s]
77%|#######7 | 32.1M/41.5M [05:12<01:23, 117kB/s]
78%|#######7 | 32.2M/41.5M [05:12<01:29, 110kB/s]
78%|#######7 | 32.2M/41.5M [05:13<01:47, 91.1kB/s]
78%|#######7 | 32.2M/41.5M [05:13<01:17, 126kB/s]
78%|#######7 | 32.2M/41.5M [05:13<01:22, 117kB/s]
78%|#######7 | 32.2M/41.5M [05:13<01:27, 110kB/s]
78%|#######7 | 32.3M/41.5M [05:13<01:31, 105kB/s]
78%|#######7 | 32.3M/41.5M [05:14<01:48, 89.2kB/s]
78%|#######7 | 32.3M/41.5M [05:14<01:18, 123kB/s]
78%|#######7 | 32.3M/41.5M [05:14<01:23, 115kB/s]
78%|#######7 | 32.4M/41.5M [05:14<01:27, 109kB/s]
78%|#######8 | 32.4M/41.5M [05:15<01:21, 117kB/s]
78%|#######8 | 32.4M/41.5M [05:15<01:17, 123kB/s]
78%|#######8 | 32.4M/41.5M [05:15<01:14, 127kB/s]
78%|#######8 | 32.4M/41.5M [05:15<01:20, 117kB/s]
78%|#######8 | 32.5M/41.5M [05:15<01:16, 124kB/s]
78%|#######8 | 32.5M/41.5M [05:15<01:13, 128kB/s]
78%|#######8 | 32.5M/41.5M [05:16<01:11, 131kB/s]
78%|#######8 | 32.5M/41.5M [05:16<01:10, 133kB/s]
78%|#######8 | 32.6M/41.5M [05:16<01:28, 106kB/s]
79%|#######8 | 32.6M/41.5M [05:16<01:16, 123kB/s]
79%|#######8 | 32.6M/41.5M [05:16<01:16, 122kB/s]
79%|#######8 | 32.6M/41.5M [05:16<01:22, 113kB/s]
79%|#######8 | 32.6M/41.5M [05:17<01:28, 105kB/s]
79%|#######8 | 32.7M/41.5M [05:17<01:21, 114kB/s]
79%|#######8 | 32.7M/41.5M [05:17<01:16, 121kB/s]
79%|#######8 | 32.7M/41.5M [05:17<01:
13, 126kB/s]
79%|#######8 | 32.7M/41.5M [05:17<01:18, 117kB/s]
79%|#######8 | 32.7M/41.5M [05:18<01:14, 123kB/s]
79%|#######8 | 32.8M/41.5M [05:18<01:11, 127kB/s]
79%|#######9 | 32.8M/41.5M [05:18<01:09, 130kB/s]
79%|#######9 | 32.8M/41.5M [05:18<01:08, 133kB/s]
79%|#######9 | 32.8M/41.5M [05:18<01:14, 121kB/s]
79%|#######9 | 32.8M/41.5M [05:19<01:33, 97.1kB/s]
79%|#######9 | 32.9M/41.5M [05:19<01:07, 133kB/s]
79%|#######9 | 32.9M/41.5M [05:19<01:08, 132kB/s]
79%|#######9 | 32.9M/41.5M [05:19<01:09, 129kB/s]
79%|#######9 | 32.9M/41.5M [05:19<01:16, 118kB/s]
79%|#######9 | 32.9M/41.5M [05:19<01:34, 94.4kB/s]
79%|#######9 | 33.0M/41.5M [05:20<01:19, 112kB/s]
80%|#######9 | 33.0M/41.5M [05:20<01:23, 107kB/s]
80%|#######9 | 33.0M/41.5M [05:20<01:26, 103kB/s]
80%|#######9 | 33.0M/41.5M [05:20<01:18, 113kB/s]
80%|#######9 | 33.0M/41.5M [05:20<01:22, 107kB/s]
80%|#######9 | 33.1M/4
1.5M [05:21<01:20, 109kB/s]
80%|#######9 | 33.1M/41.5M [05:21<01:24, 104kB/s]
80%|#######9 | 33.1M/41.5M [05:21<01:21, 108kB/s]
80%|#######9 | 33.1M/41.5M [05:21<01:19, 110kB/s]
80%|#######9 | 33.1M/41.5M [05:21<01:18, 111kB/s]
80%|#######9 | 33.2M/41.5M [05:21<01:22, 106kB/s]
80%|#######9 | 33.2M/41.5M [05:22<01:15, 115kB/s]
80%|######## | 33.2M/41.5M [05:22<01:20, 108kB/s]
80%|######## | 33.2M/41.5M [05:22<01:18, 111kB/s]
80%|######## | 33.2M/41.5M [05:22<01:15, 115kB/s]
80%|######## | 33.2M/41.5M [05:22<01:33, 92.5kB/s]
80%|######## | 33.3M/41.5M [05:23<01:27, 98.6kB/s]
80%|######## | 33.3M/41.5M [05:23<01:29, 96.3kB/s]
80%|######## | 33.3M/41.5M [05:23<01:30, 95.5kB/s]
80%|######## | 33.3M/41.5M [05:23<01:30, 94.5kB/s]
80%|######## | 33.3M/41.5M [05:23<01:31, 93.8kB/s]
80%|######## | 33.3M/41.5M [05:23<01:31, 93.4kB/s]
80%|######## | 33.4M/41.5M [05:24<01:31, 93.0kB/s]
80%|
######## | 33.4M/41.5M [05:24<01:24, 101kB/s]
80%|######## | 33.4M/41.5M [05:24<01:21, 104kB/s]
81%|######## | 33.4M/41.5M [05:24<01:17, 109kB/s]
81%|######## | 33.4M/41.5M [05:24<01:17, 109kB/s]
81%|######## | 33.4M/41.5M [05:25<01:38, 85.9kB/s]
81%|######## | 33.5M/41.5M [05:25<01:12, 116kB/s]
81%|######## | 33.5M/41.5M [05:25<01:16, 110kB/s]
81%|######## | 33.5M/41.5M [05:25<01:14, 112kB/s]
81%|######## | 33.5M/41.5M [05:25<01:18, 106kB/s]
81%|######## | 33.6M/41.5M [05:25<01:11, 116kB/s]
81%|######## | 33.6M/41.5M [05:26<01:16, 109kB/s]
81%|######## | 33.6M/41.5M [05:26<01:10, 118kB/s]
81%|########1 | 33.6M/41.5M [05:26<01:09, 118kB/s]
81%|########1 | 33.6M/41.5M [05:26<01:10, 116kB/s]
81%|########1 | 33.7M/41.5M [05:26<01:06, 123kB/s]
81%|########1 | 33.7M/41.5M [05:27<01:04, 127kB/s]
81%|########1 | 33.7M/41.5M [05:27<01:09, 117kB/s]
81%|########1 | 33.7M/41.5M [05:27<01:25, 95.3
kB/s]
81%|########1 | 33.7M/41.5M [05:27<01:03, 128kB/s]
81%|########1 | 33.8M/41.5M [05:27<01:08, 118kB/s]
81%|########1 | 33.8M/41.5M [05:27<01:08, 119kB/s]
81%|########1 | 33.8M/41.5M [05:28<01:13, 110kB/s]
81%|########1 | 33.8M/41.5M [05:28<01:07, 119kB/s]
82%|########1 | 33.8M/41.5M [05:28<01:04, 125kB/s]
82%|########1 | 33.9M/41.5M [05:28<01:30, 88.0kB/s]
82%|########1 | 33.9M/41.5M [05:29<01:11, 112kB/s]
82%|########1 | 33.9M/41.5M [05:29<01:14, 107kB/s]
82%|########1 | 33.9M/41.5M [05:29<01:17, 103kB/s]
82%|########1 | 33.9M/41.5M [05:29<01:10, 113kB/s]
82%|########1 | 34.0M/41.5M [05:29<01:05, 120kB/s]
82%|########1 | 34.0M/41.5M [05:29<01:10, 112kB/s]
82%|########1 | 34.0M/41.5M [05:30<01:05, 120kB/s]
82%|########2 | 34.0M/41.5M [05:30<01:02, 125kB/s]
82%|########2 | 34.0M/41.5M [05:30<01:00, 129kB/s]
82%|########2 | 34.1M/41.5M [05:30<00:58, 132kB/s]
82%|########2 | 34.1M/41.5M [05
:30<01:04, 120kB/s]
82%|########2 | 34.1M/41.5M [05:30<00:55, 139kB/s]
82%|########2 | 34.1M/41.5M [05:31<01:01, 125kB/s]
82%|########2 | 34.2M/41.5M [05:31<00:53, 143kB/s]
82%|########2 | 34.2M/41.5M [05:31<00:54, 142kB/s]
82%|########2 | 34.2M/41.5M [05:31<01:00, 127kB/s]
82%|########2 | 34.2M/41.5M [05:31<00:58, 130kB/s]
83%|########2 | 34.2M/41.5M [05:31<00:59, 128kB/s]
83%|########2 | 34.3M/41.5M [05:32<00:57, 131kB/s]
83%|########2 | 34.3M/41.5M [05:32<00:56, 133kB/s]
83%|########2 | 34.3M/41.5M [05:32<00:55, 135kB/s]
83%|########2 | 34.3M/41.5M [05:32<01:12, 104kB/s]
83%|########2 | 34.4M/41.5M [05:33<00:53, 139kB/s]
83%|########2 | 34.4M/41.5M [05:33<00:58, 127kB/s]
83%|########2 | 34.4M/41.5M [05:33<00:56, 130kB/s]
83%|########3 | 34.4M/41.5M [05:33<00:54, 136kB/s]
83%|########3 | 34.5M/41.5M [05:33<00:54, 136kB/s]
83%|########3 | 34.5M/41.5M [05:33<00:55, 132kB/s]
83%|########3 | 34.5
M/41.5M [05:33<00:54, 134kB/s]
83%|########3 | 34.5M/41.5M [05:34<00:49, 147kB/s]
83%|########3 | 34.5M/41.5M [05:34<00:50, 144kB/s]
83%|########3 | 34.6M/41.5M [05:34<00:51, 142kB/s]
83%|########3 | 34.6M/41.5M [05:34<00:51, 141kB/s]
83%|########3 | 34.6M/41.5M [05:34<00:51, 140kB/s]
83%|########3 | 34.6M/41.5M [05:35<01:01, 117kB/s]
83%|########3 | 34.6M/41.5M [05:35<01:05, 110kB/s]
84%|########3 | 34.7M/41.5M [05:35<00:54, 132kB/s]
84%|########3 | 34.7M/41.5M [05:35<00:55, 129kB/s]
84%|########3 | 34.7M/41.5M [05:35<00:57, 123kB/s]
84%|########3 | 34.7M/41.5M [05:36<01:12, 97.9kB/s]
84%|########3 | 34.8M/41.5M [05:36<00:53, 131kB/s]
84%|########3 | 34.8M/41.5M [05:36<00:58, 120kB/s]
84%|########3 | 34.8M/41.5M [05:36<00:58, 121kB/s]
84%|########3 | 34.8M/41.5M [05:36<01:22, 85.2kB/s]
84%|########3 | 34.8M/41.5M [05:36<01:06, 105kB/s]
84%|########3 | 34.8M/41.5M [05:37<01:17, 89.4kB/s]
84%|
########4 | 34.9M/41.5M [05:37<01:27, 79.4kB/s]
84%|########4 | 34.9M/41.5M [05:37<01:33, 73.9kB/s]
84%|########4 | 34.9M/41.5M [05:38<01:39, 69.6kB/s]
84%|########4 | 34.9M/41.5M [05:38<01:47, 64.1kB/s]
84%|########4 | 34.9M/41.5M [05:38<01:36, 71.1kB/s]
84%|########4 | 34.9M/41.5M [05:38<01:29, 76.7kB/s]
84%|########4 | 34.9M/41.5M [05:38<01:24, 81.0kB/s]
84%|########4 | 35.0M/41.5M [05:38<01:21, 84.1kB/s]
84%|########4 | 35.0M/41.5M [05:39<01:47, 63.5kB/s]
84%|########4 | 35.0M/41.5M [05:39<01:31, 74.6kB/s]
84%|########4 | 35.0M/41.5M [05:39<01:36, 70.5kB/s]
84%|########4 | 35.0M/41.5M [05:39<01:24, 80.1kB/s]
84%|########4 | 35.0M/41.5M [05:40<01:27, 77.6kB/s]
84%|########4 | 35.1M/41.5M [05:40<01:33, 72.5kB/s]
85%|########4 | 35.1M/41.5M [05:40<01:42, 65.8kB/s]
85%|########4 | 35.1M/41.5M [05:40<01:38, 68.2kB/s]
85%|########4 | 35.1M/41.5M [05:40<01:40, 66.9kB/s]
85%|########4 | 35.1M/41.5M [05:
41<01:30, 74.2kB/s]
85%|########4 | 35.1M/41.5M [05:41<01:56, 57.2kB/s]
85%|########4 | 35.1M/41.5M [05:41<01:31, 73.1kB/s]
85%|########4 | 35.1M/41.5M [05:41<01:34, 70.0kB/s]
85%|########4 | 35.2M/41.5M [05:41<01:27, 75.6kB/s]
85%|########4 | 35.2M/41.5M [05:42<02:03, 53.7kB/s]
85%|########4 | 35.2M/41.5M [05:42<01:21, 81.2kB/s]
85%|########4 | 35.2M/41.5M [05:42<01:27, 75.4kB/s]
85%|########4 | 35.2M/41.5M [05:43<01:43, 63.5kB/s]
85%|########4 | 35.2M/41.5M [05:43<01:38, 66.3kB/s]
85%|########4 | 35.3M/41.5M [05:43<01:37, 67.3kB/s]
85%|########4 | 35.3M/41.5M [05:43<01:44, 62.3kB/s]
85%|########5 | 35.3M/41.5M [05:43<01:42, 63.4kB/s]
85%|########5 | 35.3M/41.5M [05:44<01:39, 65.5kB/s]
85%|########5 | 35.3M/41.5M [05:44<01:29, 72.7kB/s]
85%|########5 | 35.3M/41.5M [05:44<01:22, 78.1kB/s]
85%|########5 | 35.3M/41.5M [05:44<01:24, 76.1kB/s]
85%|########5 | 35.3M/41.5M [05:44<01:19, 81.1kB/s]
85%
|########5 | 35.4M/41.5M [05:44<01:16, 84.5kB/s]
85%|########5 | 35.4M/41.5M [05:45<01:13, 86.9kB/s]
85%|########5 | 35.4M/41.5M [05:45<01:12, 88.5kB/s]
85%|########5 | 35.4M/41.5M [05:45<01:11, 89.7kB/s]
85%|########5 | 35.4M/41.5M [05:45<01:05, 97.0kB/s]
85%|########5 | 35.4M/41.5M [05:45<01:01, 103kB/s]
85%|########5 | 35.5M/41.5M [05:46<01:17, 81.0kB/s]
86%|########5 | 35.5M/41.5M [05:46<01:06, 94.6kB/s]
86%|########5 | 35.5M/41.5M [05:46<01:06, 94.0kB/s]
86%|########5 | 35.5M/41.5M [05:46<01:06, 93.6kB/s]
86%|########5 | 35.5M/41.5M [05:46<01:05, 95.1kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
86%|########5 | 35.6M/41.5M [05
:48<01:06, 92.3kB/s]
86%|########5 | 35.7M/41.5M [05:48<00:57, 106kB/s]
86%|########6 | 35.7M/41.5M [05:48<00:59, 102kB/s]
86%|########6 | 35.7M/41.5M [05:48<01:00, 101kB/s]
86%|########6 | 35.7M/41.5M [05:48<00:54, 110kB/s]
86%|########6 | 35.7M/41.5M [05:48<00:56, 107kB/s]
86%|########6 | 35.8M/41.5M [05:49<00:52, 114kB/s]
86%|########6 | 35.8M/41.5M [05:49<00:54, 110kB/s]
86%|########6 | 35.8M/41.5M [05:49<00:50, 118kB/s]
86%|########6 | 35.8M/41.5M [05:49<00:47, 124kB/s]
86%|########6 | 35.9M/41.5M [05:49<00:46, 126kB/s]
86%|########6 | 35.9M/41.5M [05:50<00:49, 118kB/s]
87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
87%|########6 | 36.0M/41.5M [05:50<00:41, 138kB/s]
87%|########6 | 36.0M/41.5M [05:50<00:37, 152kB/s]
87%|########6 | 36.0M/41.5M [05:51<00:38, 148kB/s]
87%|########6 | 36
.0M/41.5M [05:51<00:51, 112kB/s]
87%|########6 | 36.1M/41.5M [05:51<00:37, 153kB/s]
87%|########7 | 36.1M/41.5M [05:52<00:47, 118kB/s]
87%|########7 | 36.2M/41.5M [05:52<00:39, 141kB/s]
87%|########7 | 36.2M/41.5M [05:52<00:43, 129kB/s]
87%|########7 | 36.2M/41.5M [05:52<00:45, 122kB/s]
87%|########7 | 36.2M/41.5M [05:52<00:48, 114kB/s]
87%|########7 | 36.2M/41.5M [05:52<00:51, 108kB/s]
87%|########7 | 36.2M/41.5M [05:53<00:47, 117kB/s]
87%|########7 | 36.3M/41.5M [05:53<00:50, 110kB/s]
87%|########7 | 36.3M/41.5M [05:53<00:46, 118kB/s]
87%|########7 | 36.3M/41.5M [05:53<00:49, 110kB/s]
88%|########7 | 36.3M/41.5M [05:53<00:45, 119kB/s]
88%|########7 | 36.3M/41.5M [05:53<00:43, 125kB/s]
88%|########7 | 36.4M/41.5M [05:54<00:41, 129kB/s]
88%|########7 | 36.4M/41.5M [05:54<00:45, 118kB/s]
88%|########7 | 36.4M/41.5M [05:54<00:42, 124kB/s]
88%|########7 | 36.4M/41.5M [05:54<00:37, 142kB/s]
88%|###
#####7 | 36.5M/41.5M [05:54<00:37, 141kB/s]
88%|########7 | 36.5M/41.5M [05:55<00:37, 140kB/s]
88%|########7 | 36.5M/41.5M [05:55<00:37, 140kB/s]
88%|########8 | 36.5M/41.5M [05:55<00:44, 118kB/s]
88%|########8 | 36.6M/41.5M [05:55<00:32, 157kB/s]
88%|########8 | 36.6M/41.5M [05:55<00:36, 141kB/s]
88%|########8 | 36.6M/41.5M [05:56<00:36, 139kB/s]
88%|########8 | 36.6M/41.5M [05:56<00:46, 109kB/s]
88%|########8 | 36.7M/41.5M [05:56<00:35, 141kB/s]
88%|########8 | 36.7M/41.5M [05:56<00:47, 106kB/s]
89%|########8 | 36.7M/41.5M [05:56<00:40, 122kB/s]
89%|########8 | 36.7M/41.5M [05:57<00:43, 114kB/s]
89%|########8 | 36.8M/41.5M [05:57<00:45, 108kB/s]
89%|########8 | 36.8M/41.5M [05:57<00:51, 96.7kB/s]
89%|########8 | 36.8M/41.5M [05:57<01:02, 79.1kB/s]
89%|########8 | 36.8M/41.5M [05:58<00:52, 93.7kB/s]
89%|########8 | 36.8M/41.5M [05:58<00:59, 82.0kB/s]
89%|########8 | 36.8M/41.5M [05:58<00:57, 84.2kB
/s]
89%|########8 | 36.9M/41.5M [05:58<01:10, 68.8kB/s]
89%|########8 | 36.9M/41.5M [05:59<00:57, 84.3kB/s]
89%|########8 | 36.9M/41.5M [05:59<00:56, 86.1kB/s]
89%|########8 | 36.9M/41.5M [05:59<01:08, 69.8kB/s]
89%|########9 | 36.9M/41.5M [05:59<01:01, 77.2kB/s]
89%|########9 | 36.9M/41.5M [06:00<01:06, 71.9kB/s]
89%|########9 | 37.0M/41.5M [06:00<01:28, 54.0kB/s]
89%|########9 | 37.0M/41.5M [06:00<01:36, 49.2kB/s]
89%|########9 | 37.0M/41.5M [06:01<01:27, 53.7kB/s]
89%|########9 | 37.0M/41.5M [06:01<01:30, 52.3kB/s]
89%|########9 | 37.0M/41.5M [06:01<01:32, 51.0kB/s]
89%|########9 | 37.0M/41.5M [06:01<01:33, 49.9kB/s]
89%|########9 | 37.0M/41.5M [06:01<01:35, 49.0kB/s]
89%|########9 | 37.0M/41.5M [06:02<01:36, 48.3kB/s]
89%|########9 | 37.0M/41.5M [06:02<01:17, 60.1kB/s]
89%|########9 | 37.1M/41.5M [06:02<01:22, 56.2kB/s]
89%|########9 | 37.1M/41.5M [06:02<01:26, 53.4kB/s]
89%|########9 | 37.
1M/41.5M [06:02<01:11, 64.6kB/s]
89%|########9 | 37.1M/41.5M [06:03<01:17, 59.2kB/s]
89%|########9 | 37.1M/41.5M [06:03<01:06, 68.9kB/s]
89%|########9 | 37.1M/41.5M [06:03<01:00, 75.8kB/s]
89%|########9 | 37.1M/41.5M [06:03<00:56, 80.7kB/s]
90%|########9 | 37.1M/41.5M [06:03<00:54, 84.2kB/s]
90%|########9 | 37.2M/41.5M [06:03<00:52, 86.6kB/s]
90%|########9 | 37.2M/41.5M [06:04<00:51, 88.3kB/s]
90%|########9 | 37.2M/41.5M [06:04<00:43, 103kB/s]
90%|########9 | 37.2M/41.5M [06:04<00:34, 127kB/s]
90%|########9 | 37.3M/41.5M [06:04<00:30, 145kB/s]
90%|########9 | 37.3M/41.5M [06:04<00:28, 157kB/s]
90%|########9 | 37.3M/41.5M [06:04<00:26, 165kB/s]
90%|######### | 37.4M/41.5M [06:05<00:27, 157kB/s]
90%|######### | 37.4M/41.5M [06:05<00:22, 193kB/s]
90%|######### | 37.4M/41.5M [06:05<00:29, 146kB/s]
90%|######### | 37.5M/41.5M [06:05<00:20, 201kB/s]
90%|######### | 37.5M/41.5M [06:06<00:21, 197kB/s]
90%|######### | 37.5M/41.5M [06:06<00:22, 181kB/s]
91%|######### | 37.6M/41.5M [06:06<00:22, 182kB/s]
91%|######### | 37.6M/41.5M [06:06<00:24, 170kB/s]
91%|######### | 37.6M/41.5M [06:06<00:28, 141kB/s]
91%|######### | 37.7M/41.5M [06:07<00:25, 155kB/s]
91%|######### | 37.7M/41.5M [06:07<00:26, 151kB/s]
91%|######### | 37.7M/41.5M [06:07<00:26, 148kB/s]
91%|######### | 37.7M/41.5M [06:07<00:27, 145kB/s]
91%|#########1| 37.8M/41.5M [06:07<00:24, 156kB/s]
91%|#########1| 37.8M/41.5M [06:08<00:25, 151kB/s]
91%|#########1| 37.8M/41.5M [06:08<00:28, 137kB/s]
91%|#########1| 37.9M/41.5M [06:08<00:23, 162kB/s]
91%|#########1| 37.9M/41.5M [06:08<00:24, 155kB/s]
91%|#########1| 37.9M/41.5M [06:08<00:25, 150kB/s]
91%|#########1| 37.9M/41.5M [06:08<00:25, 146kB/s]
91%|#########1| 38.0M/41.5M [06:09<00:23, 158kB/s]
92%|#########1| 38.0M/41.5M [06:09<00:24, 152kB/s]
92%|#########1| 38.0M/41.5M [06:09<00:22, 16
2kB/s]
92%|#########1| 38.0M/41.5M [06:09<00:26, 135kB/s]
92%|#########1| 38.1M/41.5M [06:10<00:29, 123kB/s]
92%|#########1| 38.1M/41.5M [06:10<00:24, 146kB/s]
92%|#########1| 38.1M/41.5M [06:10<00:26, 133kB/s]
92%|#########1| 38.1M/41.5M [06:10<00:28, 123kB/s]
92%|#########2| 38.2M/41.5M [06:10<00:27, 127kB/s]
92%|#########2| 38.2M/41.5M [06:11<00:29, 118kB/s]
92%|#########2| 38.2M/41.5M [06:11<00:31, 110kB/s]
92%|#########2| 38.2M/41.5M [06:11<00:28, 118kB/s]
92%|#########2| 38.2M/41.5M [06:11<00:30, 111kB/s]
92%|#########2| 38.3M/41.5M [06:11<00:28, 119kB/s]
92%|#########2| 38.3M/41.5M [06:11<00:30, 111kB/s]
92%|#########2| 38.3M/41.5M [06:12<00:31, 105kB/s]
92%|#########2| 38.3M/41.5M [06:12<00:28, 115kB/s]
92%|#########2| 38.3M/41.5M [06:12<00:30, 108kB/s]
92%|#########2| 38.4M/41.5M [06:12<00:31, 104kB/s]
92%|#########2| 38.4M/41.5M [06:12<00:28, 114kB/s]
93%|#########2| 38.4M/41.5M [06:1
3<00:39, 82.7kB/s]
93%|#########2| 38.4M/41.5M [06:13<00:26, 119kB/s]
93%|#########2| 38.4M/41.5M [06:13<00:28, 112kB/s]
93%|#########2| 38.5M/41.5M [06:13<00:28, 112kB/s]
93%|#########2| 38.5M/41.5M [06:13<00:29, 107kB/s]
93%|#########2| 38.5M/41.5M [06:14<00:27, 115kB/s]
93%|#########2| 38.5M/41.5M [06:14<00:26, 117kB/s]
93%|#########2| 38.5M/41.5M [06:14<00:26, 115kB/s]
93%|#########2| 38.6M/41.5M [06:14<00:25, 122kB/s]
93%|#########3| 38.6M/41.5M [06:14<00:25, 118kB/s]
93%|#########3| 38.6M/41.5M [06:15<00:24, 124kB/s]
93%|#########3| 38.6M/41.5M [06:15<00:23, 128kB/s]
93%|#########3| 38.7M/41.5M [06:15<00:23, 127kB/s]
93%|#########3| 38.7M/41.5M [06:15<00:22, 130kB/s]
93%|#########3| 38.7M/41.5M [06:15<00:22, 133kB/s]
93%|#########3| 38.7M/41.5M [06:15<00:21, 134kB/s]
93%|#########3| 38.8M/41.5M [06:15<00:19, 147kB/s]
93%|#########3| 38.8M/41.5M [06:16<00:19, 144kB/s]
94%|#########3| 38.8
M/41.5M [06:16<00:18, 155kB/s]
94%|#########3| 38.8M/41.5M [06:16<00:24, 115kB/s]
94%|#########3| 38.9M/41.5M [06:16<00:18, 148kB/s]
94%|#########3| 38.9M/41.5M [06:16<00:19, 142kB/s]
94%|#########3| 38.9M/41.5M [06:17<00:26, 104kB/s]
94%|#########3| 38.9M/41.5M [06:17<00:19, 137kB/s]
94%|#########3| 38.9M/41.5M [06:17<00:21, 125kB/s]
94%|#########3| 39.0M/41.5M [06:17<00:21, 124kB/s]
94%|#########3| 39.0M/41.5M [06:17<00:21, 124kB/s]
94%|#########3| 39.0M/41.5M [06:17<00:21, 123kB/s]
94%|#########3| 39.0M/41.5M [06:18<00:21, 124kB/s]
94%|#########4| 39.0M/41.5M [06:18<00:22, 113kB/s]
94%|#########4| 39.0M/41.5M [06:18<00:22, 115kB/s]
94%|#########4| 39.1M/41.5M [06:18<00:20, 123kB/s]
94%|#########4| 39.1M/41.5M [06:18<00:20, 123kB/s]
94%|#########4| 39.1M/41.5M [06:18<00:25, 97.0kB/s]
94%|#########4| 39.1M/41.5M [06:19<00:20, 123kB/s]
94%|#########4| 39.1M/41.5M [06:19<00:26, 92.5kB/s]
94%|##
#######4| 39.2M/41.5M [06:19<00:24, 98.6kB/s]
94%|#########4| 39.2M/41.5M [06:19<00:25, 97.0kB/s]
94%|#########4| 39.2M/41.5M [06:20<00:25, 95.7kB/s]
94%|#########4| 39.2M/41.5M [06:20<00:25, 94.8kB/s]
95%|#########4| 39.2M/41.5M [06:20<00:25, 94.0kB/s]
95%|#########4| 39.2M/41.5M [06:20<00:25, 93.5kB/s]
95%|#########4| 39.2M/41.5M [06:20<00:25, 93.2kB/s]
95%|#########4| 39.3M/41.5M [06:20<00:25, 92.9kB/s]
95%|#########4| 39.3M/41.5M [06:21<00:24, 92.7kB/s]
95%|#########4| 39.3M/41.5M [06:21<00:24, 92.6kB/s]
95%|#########4| 39.3M/41.5M [06:21<00:21, 106kB/s]
95%|#########4| 39.3M/41.5M [06:21<00:22, 102kB/s]
95%|#########4| 39.4M/41.5M [06:21<00:19, 113kB/s]
95%|#########4| 39.4M/41.5M [06:21<00:18, 121kB/s]
95%|#########4| 39.4M/41.5M [06:22<00:19, 112kB/s]
95%|#########5| 39.4M/41.5M [06:22<00:18, 120kB/s]
95%|#########5| 39.4M/41.5M [06:22<00:17, 125kB/s]
95%|#########5| 39.5M/41.5M [06:22<00:16
, 129kB/s]
95%|#########5| 39.5M/41.5M [06:22<00:15, 132kB/s]
95%|#########5| 39.5M/41.5M [06:23<00:13, 148kB/s]
95%|#########5| 39.5M/41.5M [06:23<00:14, 145kB/s]
95%|#########5| 39.6M/41.5M [06:23<00:14, 143kB/s]
95%|#########5| 39.6M/41.5M [06:23<00:14, 142kB/s]
95%|#########5| 39.6M/41.5M [06:23<00:16, 122kB/s]
96%|#########5| 39.7M/41.5M [06:24<00:12, 152kB/s]
96%|#########5| 39.7M/41.5M [06:24<00:13, 146kB/s]
96%|#########5| 39.7M/41.5M [06:24<00:13, 144kB/s]
96%|#########5| 39.7M/41.5M [06:24<00:12, 153kB/s]
96%|#########5| 39.7M/41.5M [06:24<00:12, 148kB/s]
96%|#########5| 39.8M/41.5M [06:24<00:12, 145kB/s]
96%|#########5| 39.8M/41.5M [06:25<00:11, 157kB/s]
96%|#########5| 39.8M/41.5M [06:25<00:11, 152kB/s]
96%|#########6| 39.9M/41.5M [06:25<00:10, 161kB/s]
96%|#########6| 39.9M/41.5M [06:25<00:10, 155kB/s]
96%|#########6| 39.9M/41.5M [06:25<00:10, 164kB/s]
96%|#########6| 39.9M/41.5M [
06:25<00:10, 159kB/s]
96%|#########6| 40.0M/41.5M [06:26<00:09, 164kB/s]
96%|#########6| 40.0M/41.5M [06:26<00:09, 159kB/s]
96%|#########6| 40.0M/41.5M [06:26<00:09, 164kB/s]
97%|#########6| 40.0M/41.5M [06:26<00:08, 170kB/s]
97%|#########6| 40.1M/41.5M [06:26<00:08, 175kB/s]
97%|#########6| 40.1M/41.5M [06:27<00:10, 142kB/s]
97%|#########6| 40.1M/41.5M [06:27<00:08, 164kB/s]
97%|#########6| 40.2M/41.5M [06:27<00:08, 157kB/s]
97%|#########6| 40.2M/41.5M [06:27<00:09, 151kB/s]
97%|#########6| 40.2M/41.5M [06:27<00:08, 151kB/s]
97%|#########6| 40.2M/41.5M [06:27<00:08, 158kB/s]
97%|#########7| 40.3M/41.5M [06:28<00:07, 166kB/s]
97%|#########7| 40.3M/41.5M [06:28<00:07, 171kB/s]
97%|#########7| 40.3M/41.5M [06:28<00:06, 175kB/s]
97%|#########7| 40.4M/41.5M [06:28<00:06, 178kB/s]
97%|#########7| 40.4M/41.5M [06:28<00:06, 182kB/s]
97%|#########7| 40.4M/41.5M [06:28<00:06, 183kB/s]
97%|#########7| 40
.4M/41.5M [06:29<00:08, 131kB/s]
98%|#########7| 40.5M/41.5M [06:29<00:05, 178kB/s]
98%|#########7| 40.5M/41.5M [06:29<00:06, 167kB/s]
98%|#########7| 40.5M/41.5M [06:29<00:06, 159kB/s]
98%|#########7| 40.6M/41.5M [06:29<00:05, 166kB/s]
98%|#########7| 40.6M/41.5M [06:30<00:05, 158kB/s]
98%|#########7| 40.6M/41.5M [06:30<00:05, 166kB/s]
98%|#########7| 40.7M/41.5M [06:30<00:05, 171kB/s]
98%|#########8| 40.7M/41.5M [06:30<00:05, 162kB/s]
98%|#########8| 40.7M/41.5M [06:30<00:04, 183kB/s]
98%|#########8| 40.8M/41.5M [06:31<00:04, 169kB/s]
98%|#########8| 40.8M/41.5M [06:31<00:04, 173kB/s]
98%|#########8| 40.8M/41.5M [06:31<00:04, 178kB/s]
98%|#########8| 40.8M/41.5M [06:31<00:04, 142kB/s]
98%|#########8| 40.9M/41.5M [06:31<00:03, 167kB/s]
99%|#########8| 40.9M/41.5M [06:32<00:03, 159kB/s]
99%|#########8| 40.9M/41.5M [06:32<00:04, 125kB/s]
99%|#########8| 41.0M/41.5M [06:32<00:03, 152kB/s]
99%|###
######8| 41.0M/41.5M [06:32<00:03, 139kB/s]
99%|#########8| 41.0M/41.5M [06:32<00:03, 139kB/s]
99%|#########8| 41.0M/41.5M [06:33<00:03, 139kB/s]
99%|#########8| 41.0M/41.5M [06:33<00:03, 139kB/s]
99%|#########8| 41.1M/41.5M [06:33<00:03, 135kB/s]
99%|#########9| 41.1M/41.5M [06:33<00:03, 136kB/s]
99%|#########9| 41.1M/41.5M [06:33<00:02, 137kB/s]
99%|#########9| 41.1M/41.5M [06:33<00:03, 115kB/s]
99%|#########9| 41.1M/41.5M [06:34<00:03, 108kB/s]
99%|#########9| 41.2M/41.5M [06:34<00:03, 111kB/s]
99%|#########9| 41.2M/41.5M [06:34<00:02, 112kB/s]
99%|#########9| 41.2M/41.5M [06:34<00:03, 82.0kB/s]
99%|#########9| 41.2M/41.5M [06:35<00:02, 95.8kB/s]
99%|#########9| 41.2M/41.5M [06:35<00:03, 75.4kB/s]
99%|#########9| 41.2M/41.5M [06:35<00:03, 79.2kB/s]
99%|#########9| 41.3M/41.5M [06:35<00:02, 82.4kB/s]
99%|#########9| 41.3M/41.5M [06:35<00:02, 85.0kB/s]
100%|#########9| 41.3M/41.5M [06:36<00:02, 86.9
kB/s]
100%|#########9| 41.3M/41.5M [06:36<00:02, 88.4kB/s]
100%|#########9| 41.3M/41.5M [06:36<00:01, 89.5kB/s]
100%|#########9| 41.3M/41.5M [06:36<00:01, 84.5kB/s]
100%|#########9| 41.4M/41.5M [06:36<00:01, 86.7kB/s]
100%|#########9| 41.4M/41.5M [06:37<00:01, 72.5kB/s]
100%|#########9| 41.4M/41.5M [06:37<00:01, 89.0kB/s]
100%|#########9| 41.4M/41.5M [06:37<00:01, 71.1kB/s]
100%|#########9| 41.4M/41.5M [06:37<00:00, 75.9kB/s]
100%|#########9| 41.4M/41.5M [06:38<00:00, 75.4kB/s]
100%|#########9| 41.5M/41.5M [06:38<00:00, 72.5kB/s]
100%|#########9| 41.5M/41.5M [06:38<00:00, 65.2kB/s]
100%|#########9| 41.5M/41.5M [06:38<00:00, 53.9kB/s]
100%|##########| 41.5M/41.5M [06:38<00:00, 109kB/s]
@@ -292,6 +292,11 @@ Look up prediction top 1 index in 1000 class synset.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 7 minutes 5.320 seconds)
+
+
.. _sphx_glr_download_how_to_compile_models_from_oneflow.py:
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 2e69f5474..a9e18c6d6 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -210,7 +210,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.167 seconds)
+ **Total running time of the script:** ( 1 minutes 8.320 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 191ae8fe6..b91370a04 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -79,7 +79,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
92%|#########1| 41.0M/44.7M [00:00<00:00, 213MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
36%|###6 | 16.1M/44.7M [00:00<00:00, 167MB/s]
73%|#######3 | 32.7M/44.7M [00:00<00:00, 171MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 175MB/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 fa7a92713..cce115485 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -379,6 +379,11 @@ Run the corresponding model on tensorflow
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 8.649 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 e98f507df..278184ea5 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,15 +5,15 @@
Computation times
=================
-**05:38.395** total execution time for **how_to_compile_models** files:
+**12:07.759** total execution time for **how_to_compile_models** files:
-- **01:09.167**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **00:59.567**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:57.172**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:39.056**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:32.705**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:22.488**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:21.973**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:19.785**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:14.124**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.358**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **07:05.320**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **01:08.649**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **01:08.320**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **00:58.707**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:24.614**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:23.848**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:21.673**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:19.501**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:14.176**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.951**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 841ce2f5c..1992278fd 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -402,7 +402,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9353 15.9319 16.3844 15.7128 0.1878
+ 16.0599 15.9668 16.4660 15.8947 0.1898
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 77d3fc306..89c10d586 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -108,7 +108,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
2%|2 | 3.48M/170M [00:00<00:04, 36.5MB/s]
4%|4 | 6.97M/170M [00:00<00:05, 33.7MB/s]
18%|#7 | 30.1M/170M [00:00<00:01, 125MB/s]
29%|##8 | 49.0M/170M [00:00<00:00, 153MB/s]
43%|####2 | 72.3M/170M [00:00<00:00, 186MB/s]
56%|#####5 | 95.0M/170M [00:00<00:00, 203MB/s]
69%|######8 | 117M/170M [00:00<00:00, 210MB/s]
82%|########1 | 139M/170M [00:00<00:00, 217MB/s]
94%|#########3| 159M/170M [00:00<00:00, 189MB/s]
100%|##########| 170M/170M [00:01<00:00, 177MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 2.56M/170M [00:00<00:06, 26.5MB/s]
4%|4 | 7.06M/170M [00:00<00:04, 38.3MB/s]
7%|7 | 12.3M/170M [00:00<00:03, 45.6MB/s]
10%|9 | 16.7M/170M [00:00<00:03, 40.5MB/s]
12%|#2 | 21.0M/170M [00:00<00:03, 41.9MB/s]
15%|#4 | 25.2M/170M [00:00<00:03, 42.5MB/s]
17%|#7 | 29.3M/170M [00:00<00:04, 34.8MB/s]
19%|#9 | 32.8M/170M [00:00<00:04, 30.9MB/s]
21%|##1 | 35.9M/170M [00:01<00:05, 27.6MB/s]
23%|##2 | 38.7M/170M [00:01<00:05, 26.0MB/s]
24%|##4 | 41.4M/170M [00:01<00:05, 26.3MB/s]
26%|##5 | 44.0M/170M [00:01<00:05, 26.1MB/s]
27%|##7 | 46.5M/170M [00:01<00:04, 26.0MB/s]
29%|##8 | 49.0M/170M [00:01<00:05, 24.2MB/s]
30%|### | 51.4M/170M [00:01<00:05, 24.0MB/s]
32%|###1 | 53.7M/170M [00:01<00:05, 22.8MB/s]
33%|###2 | 55.9M/170M [00:02<00:05, 22.0MB/
s]
34%|###4 | 58.0M/170M [00:02<00:05, 22.0MB/s]
35%|###5 | 60.2M/170M [00:02<00:05, 22.2MB/s]
37%|###6 | 62.6M/170M [00:02<00:04, 23.0MB/s]
38%|###8 | 64.9M/170M [00:02<00:04, 23.4MB/s]
40%|###9 | 67.2M/170M [00:02<00:05, 19.3MB/s]
41%|#### | 69.4M/170M [00:02<00:05, 20.2MB/s]
43%|####2 | 72.4M/170M [00:02<00:04, 21.3MB/s]
45%|####5 | 76.8M/170M [00:02<00:03, 27.6MB/s]
48%|####8 | 82.0M/170M [00:03<00:02, 34.9MB/s]
51%|##### | 86.2M/170M [00:03<00:02, 37.2MB/s]
53%|#####3 | 90.4M/170M [00:03<00:02, 39.0MB/s]
56%|#####6 | 95.9M/170M [00:03<00:01, 44.5MB/s]
59%|#####9 | 100M/170M [00:03<00:01, 42.4MB/s]
61%|######1 | 104M/170M [00:03<00:01, 38.8MB/s]
64%|######3 | 108M/170M [00:03<00:01, 33.4MB/s]
66%|######6 | 112M/170M [00:03<00:01, 35.6MB/s]
69%|######8 | 117M/170M [00:03<00:01, 39.8MB/s]
71%|#######1 | 121M/170M [00:04<00:01, 3
5.2MB/s]
73%|#######3 | 125M/170M [00:04<00:01, 34.0MB/s]
75%|#######5 | 128M/170M [00:04<00:01, 29.1MB/s]
78%|#######7 | 132M/170M [00:04<00:01, 31.1MB/s]
81%|######## | 137M/170M [00:04<00:00, 38.2MB/s]
84%|########4 | 143M/170M [00:04<00:00, 44.2MB/s]
87%|########6 | 148M/170M [00:04<00:00, 40.2MB/s]
89%|########9 | 152M/170M [00:04<00:00, 40.1MB/s]
93%|#########2| 158M/170M [00:05<00:00, 45.7MB/s]
96%|#########5| 162M/170M [00:05<00:00, 47.0MB/s]
98%|#########8| 167M/170M [00:05<00:00, 43.3MB/s]
100%|##########| 170M/170M [00:05<00:00, 32.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -262,7 +262,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 56.410 seconds)
+ **Total running time of the script:** ( 3 minutes 4.324 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 078c55cf8..4b9fdf73f 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -187,7 +187,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 204MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
22%|##2 | 3.01M/13.6M [00:00<00:00, 31.4MB/s]
45%|####4 | 6.06M/13.6M [00:00<00:00, 31.5MB/s]
67%|######6 | 9.08M/13.6M [00:00<00:00, 28.6MB/s]
88%|########8 | 11.9M/13.6M [00:00<00:00, 28.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 30.3MB/s]
@@ -353,7 +353,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3360 90.2477 91.4267 90.0722 0.2370
+ 90.4285 90.3099 98.7001 90.1933 0.8536
@@ -393,7 +393,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.030 seconds)
+ **Total running time of the script:** ( 1 minutes 7.743 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 e37607571..f5323ae84 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -360,7 +360,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3097 120.1003 129.1709 119.4653 1.2372
+ 120.8243 120.7925 122.3121 120.2380 0.3238
@@ -394,7 +394,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 56.792 seconds)
+ **Total running time of the script:** ( 1 minutes 58.258 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 ebf50f1bc..819496aa5 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -223,7 +223,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 11.226 seconds)
+ **Total running time of the script:** ( 1 minutes 15.223 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 734089569..a3f9a4c82 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -137,7 +137,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
2%|1 | 2586/132723 [00:00<00:05, 25858.05KB/s]
9%|8 | 11362/132723 [00:00<00:01, 62266.11KB/s]
15%|#5 | 20231/132723 [00:00<00:01, 74327.37KB/s]
22%|##1 | 29129/132723 [00:00<00:01, 80106.91KB/s]
29%|##8 | 38051/132723 [00:00<00:01, 83389.85KB/s]
35%|###5 | 46969/132723 [00:00<00:01, 85350.78KB/s]
42%|####2 | 55905/132723 [00:00<00:00, 86656.50KB/s]
49%|####8 | 64910/132723 [00:00<00:00, 87733.14KB/s]
56%|#####5 | 73833/132723 [00:00<00:00, 88198.17KB/s]
62%|######2 | 82770/132723 [00:01<00:00, 88558.56KB/s]
69%|######9 | 91714/132723 [00:01<00:00, 88824.64KB/s]
76%|#######5 | 100775/132723 [00:01<00:00, 89365.73KB/s]
83%|########2 | 109793/132723 [00:01<00:00, 89606.85KB/s]
90%|########9 | 118843/132723 [00:01<00:00, 89874.94KB/s]
96%|#########6| 127892/132723 [00:01<00:00, 90057.50KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 85317.78KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
2%|1 | 2292/132723 [00:00<00:05, 22039.86KB/s]
5%|5 | 7205/132723 [00:00<00:03, 37708.46KB/s]
11%|#1 | 15069/132723 [00:00<00:02, 56226.20KB/s]
17%|#7 | 22575/132723 [00:00<00:01, 63618.75KB/s]
23%|##2 | 30293/132723 [00:00<00:01, 68484.68KB/s]
29%|##8 | 37929/132723 [00:00<00:01, 71152.24KB/s]
35%|###4 | 45813/132723 [00:00<00:01, 73659.68KB/s]
41%|#### | 53785/132723 [00:00<00:01, 75585.61KB/s]
47%|####6 | 61819/132723 [00:00<00:00, 77069.65KB/s]
52%|#####2 | 69541/132723 [00:01<00:00, 77107.72KB/s]
58%|#####8 | 77560/132723 [00:01<00:00, 78047.74KB/s]
64%|######4 | 85513/132723 [00:01<00:00, 78494.83KB/s]
70%|####### | 93364/132723 [00:01<00:00, 77056.50KB/s]
76%|#######6 | 101471/132723 [00:01<00:00, 78251.92KB/s]
83%|########2 | 109543/132723 [00:01<00:00, 78986.93KB/s]
88%|########8
| 117447/132723 [00:01<00:00, 78901.84KB/s]
95%|#########4| 125545/132723 [00:01<00:00, 79520.71KB/s]
100%|##########| 132723/132723 [00:01<00:00, 73670.89KB/s]
@@ -211,7 +211,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 17.943 seconds)
+ **Total running time of the script:** ( 2 minutes 20.148 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 3e006f75b..be6df573d 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**10:19.186** total execution time for **how_to_deploy_models** files:
+**10:37.507** total execution time for **how_to_deploy_models** files:
-- **02:56.410**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:17.943**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **01:56.792**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:11.226**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:06.030**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:28.090**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:22.494**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.201**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:04.324**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:20.148**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **01:58.258**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:15.223**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:07.743**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:29.021**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.584**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.205**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 776ed506f..d33bb2096 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -425,7 +425,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip75eed920-edf7-4b76-ad95-e9b3dd4ee65e from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipbacdc21b-e9b5-4639-bedc-d265e0bfc80a 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 b2091d4a1..fb7fda906 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,9 +5,9 @@
Computation times
=================
-**00:39.861** total execution time for **how_to_extend_tvm** files:
+**00:40.518** total execution time for **how_to_extend_tvm** files:
-- **00:36.153**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.382**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.119**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.208**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:36.779**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.405**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.118**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.216**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index b9c4703b1..83a914f11 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -199,10 +199,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6679us [6679us] (45.95%; 45.95%)
- FoldScaleAxis: 7856us [7us] (54.05%; 54.05%)
- FoldConstant: 7849us [1582us] (54.00%; 99.92%)
- InferType: 6268us [6268us] (43.12%; 79.85%)
+ InferType: 6481us [6481us] (45.44%; 45.44%)
+ FoldScaleAxis: 7781us [6us] (54.56%; 54.56%)
+ FoldConstant: 7775us [1596us] (54.52%; 99.92%)
+ InferType: 6179us [6179us] (43.33%; 79.47%)
@@ -239,10 +239,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6375us [6375us] (44.82%; 44.82%)
- FoldScaleAxis: 7848us [5us] (55.18%; 55.18%)
- FoldConstant: 7843us [1636us] (55.14%; 99.94%)
- InferType: 6207us [6207us] (43.64%; 79.15%)
+ InferType: 6237us [6237us] (44.69%; 44.69%)
+ FoldScaleAxis: 7720us [5us] (55.31%; 55.31%)
+ FoldConstant: 7715us [1619us] (55.28%; 99.93%)
+ InferType: 6095us [6095us] (43.68%; 79.01%)
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 34de9785b..68228633d 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -295,7 +295,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 34.746341 ms
+ Convolution: 54.227840 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 ef0438439..feba701be 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 8.828640 ms
+ conv2d with tensor core: 6.558863 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 3c2f26391..3841e1635 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -118,8 +118,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.018536
- Baseline: 3.203548
+ Numpy running time: 0.018951
+ Baseline: 3.301327
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.298506
+ Opt1: 0.314647
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.335232
+ Opt2: 0.343285
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.117339
+ Opt3: 0.117855
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110376
+ Opt4: 0.110636
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111631
+ Opt5: 0.111104
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145255
+ Opt6: 0.144939
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 94d282ed7..a9c1ba241 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:34.481** total execution time for **how_to_optimize_operators** files:
+**00:34.993** total execution time for **how_to_optimize_operators** files:
-- **00:31.760**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.493**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.228**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.370**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.393**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.231**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index 6522c4239..345304778 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:10.990** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:33.018**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:20.023**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:43.110**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.617**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.685**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.539**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:16.692** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:35.612**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:21.080**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:43.239**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:19.013**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:09.008**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.740**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index 893297b2a..99a85c611 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -222,611 +222,88 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
let cse_var_2: int32 = (rc.outer.outer*392)
let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 168), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 168), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 280), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 280), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 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 + 392), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 18), 81) < 72) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 2), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 49), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 616), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[(threadIdx.x_2*6)] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6))]
- kernel.shared_1[((threadIdx.x_2*6) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 3)]
- kernel.shared_1[((threadIdx.x_2*6) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 4)]
- kernel.shared_1[((threadIdx.x_2*6) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 5)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1[((threadIdx.x_2*6) + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 337)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 338)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 339)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 340)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 341)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3)) + 2)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 196;
+ 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" = 196;
+ 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" = 196;
+ if @tir.likely((threadIdx.x_1 < 60), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((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_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1[((threadIdx.x_2*6) + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 673)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 674)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 675)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 676)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 677)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 14), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 156), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 28), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 260), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 35), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 312), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 364), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 49), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 416), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 56), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 18)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 9) + 4), 8)*9)) + floormod(threadIdx.x_2, 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 520), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 70), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 148), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 572), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 77), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
}
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1008)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64512)]
+ for (rc.outer.inner: int32, 0, 4) {
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1728)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1737)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 648)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1224)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1800)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 657)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1233)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1809)]))
+ }
}
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1009)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64513)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1010)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64514)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1011)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64512)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1012)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64513)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1013)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64514)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
}
}
}
@@ -879,7 +356,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.209 ms
+ Execution time of this operator: 0.311 ms
@@ -925,20 +402,20 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+ conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=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=4)
- conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
@@ -946,10 +423,10 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -970,16 +447,16 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=6)
+ 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=56)
+ 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=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+ 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=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -997,588 +474,69 @@ 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__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
+ extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
__shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __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[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((9 <= ((((int)threadIdx.x) + 6) % 81)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + ((((((int)threadIdx.x) + 6) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ 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 * 392) + ((((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) + 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 * 392) + (((((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) + 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 * 392) + (((((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) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + (((((int)threadIdx.x) / 9) + 2) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 6)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6))];
- kernel_shared[((((int)threadIdx.x) * 6) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 3)];
- kernel_shared[((((int)threadIdx.x) * 6) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 4)];
- kernel_shared[((((int)threadIdx.x) * 6) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 5)];
- kernel_shared[((((int)threadIdx.x) * 6) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 337)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 338)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 339)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 340)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 341)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 673)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 674)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 675)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 676)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 677)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64512)];
+ if (((int)threadIdx.x) < 60) {
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) < 51) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1009)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64513)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1010)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64514)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1011)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64515)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1012)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64516)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1013)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64517)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 52) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 12) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 44) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 9) + 4) & 7) * 9)) + (((int)threadIdx.x) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 148) {
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 68) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1728)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1737)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 648)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1224)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1800)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 657)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1233)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1809)]));
+ }
+ }
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
}
}
@@ -1637,7 +595,7 @@ 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 33.018 seconds)
+ **Total running time of the script:** ( 2 minutes 35.612 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 62b3b53ac..72e50919f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -616,7 +616,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.7175 10.7332 10.7417 10.6776 0.0284
+ 9.9292 9.9303 9.9840 9.8732 0.0452
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 1302520fa..45f97c636 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -635,7 +635,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 751.5126 750.9964 753.1246 750.4167 1.1642
+ 759.2062 759.2453 759.2652 759.1082 0.0698
@@ -660,7 +660,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 20.023 seconds)
+ **Total running time of the script:** ( 1 minutes 21.080 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 cbdf8d162..cd9e839ec 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -362,78 +362,32 @@ 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_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- 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 (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -487,7 +441,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.840 ms
+ Execution time of this operator: 1.450 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 4d1fb0faf..e4f9b25fa 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:43.830** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.237** total execution time for **how_to_tune_with_autotvm** files:
-- **00:42.919**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.235**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.231**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.228**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
-- **00:00.217**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
+- **00:43.320**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.240**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.227**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.226**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.224**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index cf024e09e..541c33627 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -859,8 +859,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 103.02/103.02 result: MeasureResult(costs=(0.0022470772291666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6823019981384277, timestamp=1654823162.7531817) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 67.40/67.40 result: MeasureResult(costs=(0.0034348572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5976083278656006, timestamp=1654825918.712542) [('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: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -983,7 +983,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1106,7 +1106,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1229,7 +1229,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1247,7 +1247,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1370,7 +1370,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1493,7 +1493,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1616,7 +1616,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1739,7 +1739,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1862,7 +1862,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1985,7 +1985,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2108,7 +2108,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2231,7 +2231,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2319,7 +2319,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fab4438ffa2
+ 12: 0x00007f3c09a09fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 133.54/133.54 result: MeasureResult(costs=(0.0017335372258064517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1547482013702393, timestamp=1654823188.942235) [('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: 144.22/144.22 result: MeasureResult(costs=(0.00160517407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4326956272125244, timestamp=1654825945.0753632) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2437,7 +2437,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
- Time cost of this operator: 0.002110
+ Time cost of this operator: 0.002067
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 18e722c42..611ccb5f2 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -294,10 +294,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.1 98.772 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.943 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.905 0.285 (1, 1, 10, 10, 3) 1 1
- Total_time - 318.005 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.9 98.719 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.172 0.998 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.284 (1, 1, 10, 10, 3) 1 1
+ Total_time - 317.974 - - - -
@@ -359,10 +359,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 91.7 97.154 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 1.843 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.947 1.003 (1, 1, 10, 10, 3) 1 1
- Total_time - 94.386 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 321.9 99.055 (1, 3, 10, 10, 2) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.183 0.672 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.889 0.274 (1, 3, 10, 10, 1) 1 1
+ Total_time - 324.972 - - - -
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 c092541f4..df8aee133 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
@@ -297,8 +297,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp2tj1xuz5/images/target contains 8144 images
- /tmp/tmp2tj1xuz5/images/random contains 5000 images
+ /tmp/tmpbnc8mgfi/images/target contains 8144 images
+ /tmp/tmpbnc8mgfi/images/random contains 5000 images
@@ -459,11 +459,11 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 54s - loss: 0.2194 - accuracy: 0.9243 - val_loss: 0.1387 - val_accuracy: 0.9539
+ 328/328 - 54s - loss: 0.2162 - accuracy: 0.9268 - val_loss: 0.1468 - val_accuracy: 0.9581
Epoch 2/3
- 328/328 - 52s - loss: 0.0982 - accuracy: 0.9638 - val_loss: 0.1187 - val_accuracy: 0.9611
+ 328/328 - 52s - loss: 0.0937 - accuracy: 0.9649 - val_loss: 0.1316 - val_accuracy: 0.9573
Epoch 3/3
- 328/328 - 52s - loss: 0.0646 - accuracy: 0.9751 - val_loss: 0.1186 - val_accuracy: 0.9607
+ 328/328 - 52s - loss: 0.0678 - accuracy: 0.9746 - val_loss: 0.1096 - val_accuracy: 0.9622
@@ -825,7 +825,7 @@ 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 55.643 seconds)
+ **Total running time of the script:** ( 4 minutes 12.281 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 cf56e728c..d877e6808 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
@@ -5,11 +5,11 @@
Computation times
=================
-**05:42.129** total execution time for **how_to_work_with_microtvm** files:
+**04:58.551** total execution time for **how_to_work_with_microtvm** files:
-- **04:55.643**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
-- **00:42.149**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.719**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **04:12.281**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``)
+- **00:41.955**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.688**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.214**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
- **00:00.206**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
-- **00:00.205**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index ca1ec3dfe..7a77d874a 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:11.746** total execution time for **how_to_work_with_relay** files:
+**00:11.749** total execution time for **how_to_work_with_relay** files:
-- **00:09.907**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:01.617**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
-- **00:00.222**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
+- **00:10.033**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.491**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.225**: :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
index b44efe903..1169bee66 100644
--- a/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/sg_execution_times.rst.txt
@@ -5,13 +5,13 @@
Computation times
=================
-**00:05.749** total execution time for **how_to_work_with_schedules** files:
+**00:05.613** total execution time for **how_to_work_with_schedules** files:
-- **00:02.101**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.160**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.743**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.717**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.317**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.253**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.229**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.228**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.011**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.132**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.717**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.706**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.318**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.251**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.247**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.231**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index 25e73f11d..020f56546 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -318,7 +318,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmprceh4wqg/input0.cc'\nsource_filename = \"/tmp/tmprceh4wqg/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/tmppvfr2ekq/input0.cc'\nsource_filename = \"/tmp/tmppvfr2ekq/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 e03d877cf..ca155f74e 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:21.527** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.440** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:21.310**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.217**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:21.221**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.220**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 398cb1e4a..2dca163ee 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -267,7 +267,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.03s!
+ resnet18_v1 inference graph built in 22.65s!
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 3c216b0bf..fa6d510f1 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -303,7 +303,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.49s!
+ yolov3-tiny inference graph built in 15.81s!
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 4f98a2f79..2b5b666a0 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**01:28.771** total execution time for **topic_vta_tutorials_frontend** files:
+**01:30.874** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:47.119**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.652**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:47.984**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:42.890**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index bb7c2c580..97f04a07c 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:03.627** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.610** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.046**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.581**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:03.037**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.573**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index b05accc57..57dd3a5e2 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:01.063** total execution time for **topic_vta_tutorials** files:
+**00:01.067** total execution time for **topic_vta_tutorials** files:
-- **00:00.539**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.524**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.549**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.519**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 065cafb17..53d97fbe8 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.253 ms
+ Execution time of this operator: 94.379 ms
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index fae8ea159..c7c732601 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -280,7 +280,7 @@ standard deviation.
.. code-block:: none
- {'mean': 493.9747734299987, 'median': 493.3764933999953, 'std': 1.577059224609088}
+ {'mean': 495.59848807000435, 'median': 495.2797966999924, 'std': 1.0106395046662517}
@@ -494,31 +494,31 @@ the tuning data to.
.. code-block:: none
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.38/ 17.38 GFLOPS | Progress: (4/20) | 5.59 s
[Task 1/25] Current/Best: 6.17/ 17.38 GFLOPS | Progress: (8/20) | 9.04 s
[Task 1/25] Current/Best: 11.55/ 22.83 GFLOPS | Progress: (12/20) | 11.50 s
[Task 1/25] Current/Best: 16.74/ 22.87 GFLOPS | Progress: (16/20) | 13.17 s
[Task 1/25] Current/Best: 11.62/ 23.53 GFLOPS | Progress: (20/20) | 14.89 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.31/ 12.97 GFLOPS | Progress: (4/20) | 3.82 s
[Task 2/25] Current/Best: 14.21/ 18.30 GFLOPS | Progress: (8/20) | 5.15 s
[Task 2/25] Current/Best: 21.22/ 21.22 GFLOPS | Progress: (12/20) | 6.49 s
[Task 2/25] Current/Best: 12.83/ 21.22 GFLOPS | Progress: (16/20) | 7.76 s
[Task 2/25] Current/Best: 20.04/ 21.22 GFLOPS | Progress: (20/20) | 9.39 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/ 10.30 GFLOPS | Progress: (4/20) | 5.81 s
[Task 3/25] Current/Best: 15.54/ 16.83 GFLOPS | Progress: (8/20) | 7.72 s
[Task 3/25] Current/Best: 14.91/ 16.83 GFLOPS | Progress: (12/20) | 9.43 s
[Task 3/25] Current/Best: 7.19/ 23.74 GFLOPS | Progress: (16/20) | 11.36 s
[Task 3/25] Current/Best: 12.65/ 23.74 GFLOPS | Progress: (20/20) | 15.94 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 20.14 GFLOPS | Progress: (4/20) | 2.32 s
[Task 4/25] Current/Best: 6.87/ 20.14 GFLOPS | Progress: (8/20) | 7.04 s
[Task 4/25] Current/Best: 22.04/ 22.04 GFLOPS | Progress: (12/20) | 11.94 s
[Task 4/25] Current/Best: 16.58/ 22.04 GFLOPS | Progress: (16/20) | 14.40 s
[Task 4/25] Current/Best: 13.23/ 22.04 GFLOPS | Progress: (20/20) | 16.39 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.79/ 10.47 GFLOPS | Progress: (4/20) | 2.53 s
[Task 5/25] Current/Best: 11.92/ 12.79 GFLOPS | Progress: (8/20) | 4.57 s
[Task 5/25] Current/Best: 11.61/ 18.08 GFLOPS | Progress: (12/20) | 7.80 s
[Task 5/25] Current/Best: 11.83/ 22.65 GFLOPS | Progress: (16/20) | 9.20 s
[Task 5/25] Current/Best: 12.05/ 22.65 GFLOPS | Progress: (20/20) | 11.09 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.34/ 20.67 GFLOPS | Progress: (4/20) | 4.03 s
[Task 6/25] Current/Best: 18.96/ 20.67 GFLOPS | Progress: (8/20) | 5.78 s
[Task 6/25] Current/Best: 13.25/ 20.67 GFLOPS | Progress: (12/20) | 7.73 s
[Task 6/25] Current/Best: 20.02/ 20.67 GFLOPS | Progress: (16/20) | 9.95 s
[Task 6/25] Current/Best: 3.73/ 20.67 GFLOPS | Progress: (20/20) | 12.44 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.22/ 12.44 GFLOPS | Progress: (4/20) | 3.56 s
[Task 7/25] Current/Best: 20.30/ 21.26 GFLOPS | Progress: (8/20) | 5.06 s
[Task 7/25] Current/Best: 16.00/ 21.26 GFLOPS | Progress: (12/20) | 6.96 s
[Task 7/25] Current/Best: 12.24/ 21.26 GFLOPS | Progress: (16/20) | 9.00 s
[Task 7/25] Current/Best: 6.44/ 21.82 GFLOPS | Progress: (20/20) | 11.45 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.36/ 14.34 GFLOPS | Progress: (4/20) | 2.82 s
[Task 8/25] Current/Best: 9.99/ 14.34 GFLOPS | Progress: (8/20) | 7.89 s
[Task 8/25] Current/Best: 12.82/ 14.34 GFLOPS | Progress: (12/20) | 14.45 s
[Task 8/25] Current/Best: 18.81/ 18.81 GFLOPS | Progress: (16/20) | 16.55 s
[Task 8/25] Current/Best: 19.32/ 19.32 GFLOPS | Progress: (20/20) | 23.67 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.33/ 15.77 GFLOPS | Progress: (4/20) | 11.89 s
[Task 9/25] Current/Best: 23.41/ 23.41 GFLOPS | Progress: (8/20) | 13.66 s
[Task 9/25] Current/Best: 8.28/ 23.41 GFLOPS | Progress: (12/20) | 16.17 s
[Task 9/25] Current/Best: 17.93/ 23.41 GFLOPS | Progress: (16/20) | 18.92 s
[Task 9/25] Current/Best: 8.99/ 23.41 GFLOPS | Progress: (20/20) | 27.56 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (4/20) | 2.51 s
[Task 10/25] Current/Best: 15.57/ 18.19 GFLOPS | Progress: (8/20) | 4.14 s
[Task 10/25] Current/Best: 12.60/ 19.00 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.17/ 20.41 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.93/ 20.41 GFLOPS | Progress: (20/20
) | 8.32 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.97/ 18.16 GFLOPS | Progress: (4/20) | 3.32 s
[Task 11/25] Current/Best: 16.82/ 18.16 GFLOPS | Progress: (8/20) | 6.16 s
[Task 11/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 8.22 s
[Task 11/25] Current/Best: 13.54/ 21.26 GFLOPS | Progress: (16/20) | 11.09 s
[Task 11/25] Current/Best: 19.39/ 21.57 GFLOPS | Progress: (20/20) | 13.18 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.76/ 18.00 GFLOPS | Progress: (4/20) | 5.65 s
[Task 12/25] Current/Best: 5.31/ 18.00 GFLOPS | Progress: (8/20) | 9.56 s
[Task 12/25] Current/Best: 18.50/ 18.92 GFLOPS | Progress: (12/20) | 11.54 s
[Task 12/25] Current/Best: 15.11/ 18.92 GFLOPS | Progress: (16/20) | 14.48 s
[Task 12/25] Current/Best: 15.07/ 18.94 GFLOPS | Progress: (20/20) | 16.39 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.75/ 17.32 GFLOPS | Progress: (4/20) | 3.70 s
[Task 13/25] Current/Best: 15.61/ 20.86 GFLOPS | Progress: (8/20) | 6.32 s
[Task 13/25] Current/Best: 19.53/ 21.18 GFLOPS | Progress: (12/20) | 9.29 s
[Task 13/25] Current/Best: 12.28/ 21.18 GFLOPS | Progress: (16/20) | 12.76 s
[Task 13/25] Current/Best: 18.69/ 21.18 GFLOPS | Progress: (20/20) | 15.11 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.59/ 13.59 GFLOPS | Progress: (4/20) | 3.32 s
[Task 14/25] Current/Best: 6.10/ 13.59 GFLOPS | Progress: (8/20) | 5.48 s
[Task 14/25] Current/Best: 21.09/ 21.09 GFLOPS | Progress: (12/20) | 8.16 s
[Task 14/25] Current/Best: 16.85/ 21.09 GFLOPS | Progress: (16/20) | 9.83 s Done.
-
[Task 14/25] Current/Best: 17.27/ 21.09 GFLOPS | Progress: (20/20) | 11.54 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.23/ 17.71 GFLOPS | Progress: (4/20) | 2.59 s
[Task 15/25] Current/Best: 13.39/ 18.07 GFLOPS | Progress: (8/20) | 3.97 s
[Task 15/25] Current/Best: 10.38/ 22.35 GFLOPS | Progress: (12/20) | 6.22 s
[Task 15/25] Current/Best: 20.45/ 22.35 GFLOPS | Progress: (16/20) | 9.22 s
[Task 15/25] Current/Best: 9.70/ 22.35 GFLOPS | Progress: (20/20) | 10.18 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (4/20) | 2.85 s
[Task 16/25] Current/Best: 3.03/ 20.65 GFLOPS | Progress: (8/20) | 4.49 s
[Task 16/25] Current/Best: 19.07/ 20.65 GFLOPS | Progress: (12/20) | 5.70 s
[Task 16/25] Current/Best: 18.22/ 20.65 GFLOPS | Progress: (16/20) |
7.07 s
[Task 16/25] Current/Best: 9.99/ 22.29 GFLOPS | Progress: (20/20) | 9.22 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.04/ 18.96 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.25/ 23.39 GFLOPS | Progress: (8/20) | 7.56 s
[Task 17/25] Current/Best: 16.81/ 23.39 GFLOPS | Progress: (12/20) | 9.62 s
[Task 17/25] Current/Best: 16.49/ 23.39 GFLOPS | Progress: (16/20) | 11.85 s
[Task 17/25] Current/Best: 10.03/ 23.39 GFLOPS | Progress: (20/20) | 14.01 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.29/ 17.91 GFLOPS | Progress: (4/20) | 3.78 s
[Task 18/25] Current/Best: 10.62/ 20.18 GFLOPS | Progress: (8/20) | 7.47 s
[Task 18/25] Current/Best: 19.25/ 20.18 GFLOPS | Progress: (12/20) | 9.40 s
[Task 18/25] Current/Best: 10.03/ 20.18 GFLOPS | Progress: (16/20) | 13.29 s
[Task 18/25] Current/Best: 20.97/ 20.97 GFLOPS | Progress: (20/20) | 14.78 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.12/ 20.43 GFLOPS | Progress: (4/20) | 6.05 s
[Task 19/25] Current/Best: 2.61/ 20.43 GFLOPS | Progress: (8/20) | 9.37 s
[Task 19/25] Current/Best: 19.96/ 21.70 GFLOPS | Progress: (12/20) | 12.31 s
[Task 19/25] Current/Best: 15.24/ 21.70 GFLOPS | Progress: (16/20) | 15.32 s
[Task 19/25] Current/Best: 2.70/ 23.44 GFLOPS | Progress: (20/20) | 18.11 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.39/ 15.17 GFLOPS | Progress: (4/20) | 3.28 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.47/ 17.47 GFLOPS | Progress: (4/20) | 5.59 s
[Task 1/25] Current/Best: 6.16/ 17.47 GFLOPS | Progress: (8/20) | 8.93 s
[Task 1/25] Current/Best: 11.50/ 22.79 GFLOPS | Progress: (12/20) | 11.39 s
[Task 1/25] Current/Best: 16.84/ 22.79 GFLOPS | Progress: (16/20) | 13.09 s
[Task 1/25] Current/Best: 11.62/ 23.93 GFLOPS | Progress: (20/20) | 14.81 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.30/ 13.29 GFLOPS | Progress: (4/20) | 3.86 s
[Task 2/25] Current/Best: 14.01/ 18.77 GFLOPS | Progress: (8/20) | 5.16 s
[Task 2/25] Current/Best: 21.13/ 21.13 GFLOPS | Progress: (12/20) | 6.48 s
[Task 2/25] Current/Best: 12.56/ 21.13 GFLOPS | Progress: (16/20) | 7.74 s
[Task 2/25] Current/Best: 19.72/ 21.13 GFLOPS | Progress: (20/20) | 9.37 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/ 10.54 GFLOPS | Progress: (4/20) | 5.79 s
[Task 3/25] Current/Best: 15.56/ 16.82 GFLOPS | Progress: (8/20) | 7.71 s
[Task 3/25] Current/Best: 14.86/ 16.82 GFLOPS | Progress: (12/20) | 9.42 s
[Task 3/25] Current/Best: 7.19/ 23.75 GFLOPS | Progress: (16/20) | 11.36 s
[Task 3/25] Current/Best: 11.16/ 23.75 GFLOPS | Progress: (20/20) | 15.99 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.51/ 20.17 GFLOPS | Progress: (4/20) | 2.32 s
[Task 4/25] Current/Best: 6.85/ 20.17 GFLOPS | Progress: (8/20) | 7.05 s
[Task 4/25] Current/Best: 22.28/ 22.28 GFLOPS | Progress: (12/20) | 12.08 s
[Task 4/25] Current/Best: 17.37/ 22.28 GFLOPS | Progress: (16/20) | 14.54 s
[Task 4/25] Current/Best: 13.34/ 22.28 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.63/ 10.28 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.60/ 12.07 GFLOPS | Progress: (8/20) | 4.60 s
[Task 5/25] Current/Best: 11.29/ 18.14 GFLOPS | Progress: (12/20) | 7.68 s
[Task 5/25] Current/Best: 11.88/ 22.66 GFLOPS | Progress: (16/20) | 9.11 s
[Task 5/25] Current/Best: 12.05/ 22.66 GFLOPS | Progress: (20/20) | 10.98 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.28/ 20.72 GFLOPS | Progress: (4/20) | 4.05 s
[Task 6/25] Current/Best: 18.94/ 20.72 GFLOPS | Progress: (8/20) | 5.81 s
[Task 6/25] Current/Best: 13.29/ 20.72 GFLOPS | Progress: (12/20) | 7.76 s
[Task 6/25] Current/Best: 19.99/ 20.72 GFLOPS | Progress: (16/20) | 9.98 s
[Task 6/25] Current/Best: 3.74/ 20.72 GFLOPS | Progress: (20/20) | 12.48 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.18/ 12.77 GFLOPS | Progress: (4/20) | 3.56 s
[Task 7/25] Current/Best: 20.02/ 21.12 GFLOPS | Progress: (8/20) | 5.06 s
[Task 7/25] Current/Best: 15.99/ 21.12 GFLOPS | Progress: (12/20) | 7.01 s
[Task 7/25] Current/Best: 12.24/ 21.12 GFLOPS | Progress: (16/20) | 9.06 s
[Task 7/25] Current/Best: 6.39/ 21.70 GFLOPS | Progress: (20/20) | 11.50 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.13/ 14.29 GFLOPS | Progress: (4/20) | 2.87 s
[Task 8/25] Current/Best: 9.67/ 14.29 GFLOPS | Progress: (8/20) | 8.08 s
[Task 8/25] Current/Best: 12.66/ 14.29 GFLOPS | Progress: (12/20) | 14.65 s
[Task 8/25] Current/Best: 18.68/ 18.68 GFLOPS | Progress: (16/20) | 16.73 s
[Task 8/25] Current/Best: 20.13/ 20.13 GFLOPS | Progress: (20/20) | 23.83 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.22/ 15.71 GFLOPS | Progress: (4/20) | 11.89 s
[Task 9/25] Current/Best: 23.34/ 23.34 GFLOPS | Progress: (8/20) | 13.59 s
[Task 9/25] Current/Best: 8.27/ 23.34 GFLOPS | Progress: (12/20) | 16.14 s
[Task 9/25] Current/Best: 17.96/ 23.34 GFLOPS | Progress: (16/20) | 19.02 s
[Task 9/25] Current/Best: 8.97/ 23.34 GFLOPS | Progress: (20/20) | 27.79 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 17.99/ 17.99 GFLOPS | Progress: (4/20) | 2.51 s
[Task 10/25] Current/Best: 15.51/ 17.99 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 11.48/ 18.89 GFLOPS | Progress: (12/20) | 5.71 s
[Task 10/25] Current/Best: 18.98/ 20.31 GFLOPS | Progress: (16/20) | 6.82 s
[Task 10/25] Current/Best: 8.84/ 20.31 GFLOPS | Progress: (20/20
) | 8.34 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.14/ 18.12 GFLOPS | Progress: (4/20) | 3.30 s
[Task 11/25] Current/Best: 17.01/ 18.12 GFLOPS | Progress: (8/20) | 6.13 s
[Task 11/25] Current/Best: 18.16/ 18.16 GFLOPS | Progress: (12/20) | 8.20 s
[Task 11/25] Current/Best: 13.41/ 21.15 GFLOPS | Progress: (16/20) | 11.17 s
[Task 11/25] Current/Best: 19.44/ 21.55 GFLOPS | Progress: (20/20) | 13.29 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.79/ 18.02 GFLOPS | Progress: (4/20) | 5.73 s
[Task 12/25] Current/Best: 5.18/ 18.02 GFLOPS | Progress: (8/20) | 9.67 s
[Task 12/25] Current/Best: 18.92/ 18.92 GFLOPS | Progress: (12/20) | 11.65 s
[Task 12/25] Current/Best: 15.24/ 18.92 GFLOPS | Progress: (16/20) | 14.60 s
[Task 12/25] Current/Best: 15.08/ 18.96 GFLOPS | Progress: (20/20) | 16.51 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.83/ 17.24 GFLOPS | Progress: (4/20) | 3.68 s
[Task 13/25] Current/Best: 16.04/ 20.87 GFLOPS | Progress: (8/20) | 6.30 s
[Task 13/25] Current/Best: 19.45/ 20.87 GFLOPS | Progress: (12/20) | 9.32 s
[Task 13/25] Current/Best: 12.24/ 20.87 GFLOPS | Progress: (16/20) | 12.76 s
[Task 13/25] Current/Best: 18.77/ 20.87 GFLOPS | Progress: (20/20) | 15.06 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.65/ 13.65 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.07/ 13.65 GFLOPS | Progress: (8/20) | 5.52 s
[Task 14/25] Current/Best: 20.61/ 20.61 GFLOPS | Progress: (12/20) | 8.21 s
[Task 14/25] Current/Best: 16.61/ 20.61 GFLOPS | Progress: (16/20) | 9.88 s Done.
+
[Task 14/25] Current/Best: 17.27/ 20.61 GFLOPS | Progress: (20/20) | 11.57 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.18/ 17.61 GFLOPS | Progress: (4/20) | 2.63 s
[Task 15/25] Current/Best: 14.47/ 18.07 GFLOPS | Progress: (8/20) | 3.93 s
[Task 15/25] Current/Best: 10.39/ 22.24 GFLOPS | Progress: (12/20) | 6.18 s
[Task 15/25] Current/Best: 20.40/ 22.24 GFLOPS | Progress: (16/20) | 9.42 s
[Task 15/25] Current/Best: 9.63/ 22.24 GFLOPS | Progress: (20/20) | 10.45 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.14/ 20.14 GFLOPS | Progress: (4/20) | 2.86 s
[Task 16/25] Current/Best: 3.04/ 20.14 GFLOPS | Progress: (8/20) | 4.48 s
[Task 16/25] Current/Best: 18.90/ 20.14 GFLOPS | Progress: (12/20) | 5.70 s
[Task 16/25] Current/Best: 17.96/ 20.14 GFLOPS | Progress: (16/20) |
7.08 s
[Task 16/25] Current/Best: 9.96/ 22.55 GFLOPS | Progress: (20/20) | 9.24 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.83/ 18.89 GFLOPS | Progress: (4/20) | 4.74 s
[Task 17/25] Current/Best: 14.39/ 23.30 GFLOPS | Progress: (8/20) | 7.54 s
[Task 17/25] Current/Best: 16.83/ 23.30 GFLOPS | Progress: (12/20) | 9.58 s
[Task 17/25] Current/Best: 16.78/ 23.30 GFLOPS | Progress: (16/20) | 11.82 s
[Task 17/25] Current/Best: 9.98/ 23.30 GFLOPS | Progress: (20/20) | 13.97 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.52/ 17.56 GFLOPS | Progress: (4/20) | 3.72 s
[Task 18/25] Current/Best: 10.59/ 19.95 GFLOPS | Progress: (8/20) | 7.42 s
[Task 18/25] Current/Best: 19.40/ 19.95 GFLOPS | Progress: (12/20) | 9.35 s
[Task 18/25] Current/Best: 9.96/ 19.95 GFLOPS | Progress: (16/20) | 13.25 s
[Task 18/25] Current/Best: 20.80/ 20.80 GFLOPS | Progress: (20/20) | 14.76 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.83/ 20.39 GFLOPS | Progress: (4/20) | 6.12 s
[Task 19/25] Current/Best: 2.60/ 20.39 GFLOPS | Progress: (8/20) | 9.45 s
[Task 19/25] Current/Best: 19.53/ 20.99 GFLOPS | Progress: (12/20) | 12.41 s
[Task 19/25] Current/Best: 15.22/ 20.99 GFLOPS | Progress: (16/20) | 15.38 s
[Task 19/25] Current/Best: 2.70/ 23.23 GFLOPS | Progress: (20/20) | 18.18 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/ 15.07 GFLOPS | Progress: (4/20) | 3.29 s Done.
Done.
-
[Task 20/25] Current/Best: 9.75/ 15.17 GFLOPS | Progress: (8/20) | 6.80 s
[Task 20/25] Current/Best: 2.33/ 15.63 GFLOPS | Progress: (12/20) | 10.69 s
[Task 20/25] Current/Best: 12.56/ 15.63 GFLOPS | Progress: (16/20) | 14.46 s
[Task 20/25] Current/Best: 11.84/ 21.40 GFLOPS | Progress: (20/20) | 16.58 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.41/ 17.72 GFLOPS | Progress: (4/20) | 3.21 s
[Task 21/25] Current/Best: 14.63/ 17.72 GFLOPS | Progress: (8/20) | 4.84 s
[Task 21/25] Current/Best: 1.61/ 17.72 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 18.04/ 18.04 GFLOPS | Progress: (16/20) | 10.47 s
[Task 21/25] Current/Best: 4.47/ 18.04 GFLOPS | Progress: (20/20) | 17.77 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.98 GFLOPS | Progress: (4/20
) | 2.62 s
[Task 22/25] Current/Best: 9.09/ 21.22 GFLOPS | Progress: (8/20) | 4.66 s
[Task 22/25] Current/Best: 19.36/ 21.22 GFLOPS | Progress: (12/20) | 7.02 s
[Task 22/25] Current/Best: 14.83/ 21.22 GFLOPS | Progress: (16/20) | 9.15 s
[Task 22/25] Current/Best: 14.07/ 21.22 GFLOPS | Progress: (20/20) | 10.89 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.52/ 20.74 GFLOPS | Progress: (4/20) | 3.16 s
[Task 23/25] Current/Best: 14.90/ 20.74 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 20.95/ 21.77 GFLOPS | Progress: (12/20) | 8.37 s
[Task 23/25] Current/Best: 6.35/ 21.77 GFLOPS | Progress: (16/20) | 15.32 s
[Task 23/25] Current/Best: 7.68/ 21.77 GFLOPS | Progress: (20/20) | 19.54 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) | 11.75 s
[Task 24/25] Current/Best: 3.67/ 8.50 GFLOPS | Progress: (8/20) | 22.94 s
[Task 24/25] Current/Best: 4.52/ 8.50 GFLOPS | Progress: (12/20) | 33.67 s Done.
+
[Task 20/25] Current/Best: 10.05/ 15.07 GFLOPS | Progress: (8/20) | 6.69 s
[Task 20/25] Current/Best: 2.32/ 16.65 GFLOPS | Progress: (12/20) | 10.65 s
[Task 20/25] Current/Best: 12.48/ 16.65 GFLOPS | Progress: (16/20) | 14.43 s
[Task 20/25] Current/Best: 13.47/ 21.72 GFLOPS | Progress: (20/20) | 16.54 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.62 GFLOPS | Progress: (4/20) | 3.22 s
[Task 21/25] Current/Best: 14.61/ 17.62 GFLOPS | Progress: (8/20) | 4.85 s
[Task 21/25] Current/Best: 1.61/ 17.62 GFLOPS | Progress: (12/20) | 6.96 s
[Task 21/25] Current/Best: 17.85/ 17.85 GFLOPS | Progress: (16/20) | 10.49 s
[Task 21/25] Current/Best: 4.47/ 17.85 GFLOPS | Progress: (20/20) | 17.83 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.09 GFLOPS | Progress: (4/20
) | 2.62 s
[Task 22/25] Current/Best: 9.08/ 21.86 GFLOPS | Progress: (8/20) | 4.66 s
[Task 22/25] Current/Best: 20.05/ 21.86 GFLOPS | Progress: (12/20) | 7.08 s
[Task 22/25] Current/Best: 15.45/ 21.86 GFLOPS | Progress: (16/20) | 9.24 s
[Task 22/25] Current/Best: 14.38/ 21.86 GFLOPS | Progress: (20/20) | 10.98 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/ 20.43 GFLOPS | Progress: (4/20) | 3.20 s
[Task 23/25] Current/Best: 15.24/ 20.43 GFLOPS | Progress: (8/20) | 6.49 s
[Task 23/25] Current/Best: 20.76/ 21.32 GFLOPS | Progress: (12/20) | 8.35 s
[Task 23/25] Current/Best: 6.25/ 21.32 GFLOPS | Progress: (16/20) | 15.53 s
[Task 23/25] Current/Best: 7.58/ 21.32 GFLOPS | Progress: (20/20) | 19.78 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.79/ 8.79 GFLOPS | Progress: (4/20) | 11.73 s
[Task 24/25] Current/Best: 2.13/ 8.79 GFLOPS | Progress: (8/20) | 22.75 s
[Task 24/25] Current/Best: 4.38/ 8.79 GFLOPS | Progress: (12/20) | 34.25 s Done.
Done.
-
[Task 24/25] Current/Best: 7.38/ 8.90 GFLOPS | Progress: (16/20) | 39.42 s
[Task 24/25] Current/Best: 3.29/ 8.99 GFLOPS | Progress: (20/20) | 45.36 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.56/ 2.87 GFLOPS | Progress: (4/20) | 11.54 s
[Task 25/25] Current/Best: 6.02/ 8.01 GFLOPS | Progress: (8/20) | 22.77 s
[Task 25/25] Current/Best: 5.91/ 8.01 GFLOPS | Progress: (12/20) | 34.17 s
[Task 25/25] Current/Best: 5.86/ 9.54 GFLOPS | Progress: (16/20) | 36.03 s
[Task 25/25] Current/Best: 2.85/ 9.54 GFLOPS | Progress: (20/20) | 46.76 s
+
[Task 24/25] Current/Best: 6.90/ 8.92 GFLOPS | Progress: (16/20) | 40.30 s
[Task 24/25] Current/Best: 3.31/ 9.17 GFLOPS | Progress: (20/20) | 46.24 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/ 2.90 GFLOPS | Progress: (4/20) | 11.55 s
[Task 25/25] Current/Best: 5.84/ 7.88 GFLOPS | Progress: (8/20) | 22.77 s
[Task 25/25] Current/Best: 5.81/ 7.88 GFLOPS | Progress: (12/20) | 34.03 s
[Task 25/25] Current/Best: 5.71/ 9.43 GFLOPS | Progress: (16/20) | 35.92 s
[Task 25/25] Current/Best: 2.93/ 9.43 GFLOPS | Progress: (20/20) | 46.66 s
The output from this tuning process will look something like this:
@@ -660,8 +660,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 410.6713519799973, 'median': 410.5332598500013, 'std': 0.8896911438117638}
- unoptimized: {'mean': 493.9747734299987, 'median': 493.3764933999953, 'std': 1.577059224609088}
+ optimized: {'mean': 412.10542912999244, 'median': 411.9932389499809, 'std': 0.8686640765925975}
+ unoptimized: {'mean': 495.59848807000435, 'median': 495.2797966999924, 'std': 1.0106395046662517}
@@ -681,7 +681,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 18.190 seconds)
+ **Total running time of the script:** ( 10 minutes 24.041 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 627766b2c..c65295593 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -235,7 +235,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.257e-07 secs/op
+ 1.32e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 4c4160f32..831c9235d 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -232,7 +232,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x65b7f70)), stage(b, placeholder(b, 0x1fd25940)), 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, 0x2146a290)), stage(b, placeholder(b, 0x281cee20)), 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 9be542eae..94f1b86ad 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,17 +5,17 @@
Computation times
=================
-**13:07.710** total execution time for **tutorial** files:
+**13:09.560** total execution time for **tutorial** files:
-- **10:18.190**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **00:58.843**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:57.258**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **00:27.942**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:23.351**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.045**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.722**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.222**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.037**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.035**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.034**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.031**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **10:24.041**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **01:00.772**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:51.081**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:28.398**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:23.561**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:00.734**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.575**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.213**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.048**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **00:00.047**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.047**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.045**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index cd120a3b9..835ecdbdb 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -252,7 +252,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000007
+ Numpy running time: 0.000009
naive: 0.000006
@@ -344,7 +344,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000010
+ parallel: 0.000009
@@ -397,7 +397,7 @@ factor to be the number of threads on your CPU.
.. code-block:: none
- vector: 0.000026
+ vector: 0.000025
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [(stride: int32*n: int32)], [], type="auto"),
@@ -447,10 +447,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 7.085330000791146e-06 1.0
- naive 5.8064e-06 0.8194960572551538
- parallel 9.6339e-06 1.3596967253359096
- vector 2.6281900000000003e-05 3.709340284371423
+ numpy 8.54919999710546e-06 1.0
+ naive 5.8444e-06 0.6836195201865395
+ parallel 8.7372e-06 1.0219903620172872
+ vector 2.4615899999999996e-05 2.8793220428033393
@@ -839,7 +839,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018178
+ Numpy running time: 0.018437
@@ -897,7 +897,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.245746
+ none: 3.386214
@@ -996,7 +996,7 @@ schedule.
.. code-block:: none
- blocking: 0.301983
+ blocking: 0.309929
@@ -1088,7 +1088,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.339595
+ vectorization: 0.346366
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1160,7 +1160,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.119652
+ loop permutation: 0.117646
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1257,7 +1257,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.112054
+ array packing: 0.108238
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1348,7 +1348,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.111041
+ block caching: 0.110372
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1432,7 +1432,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.144525
+ parallelization: 0.144301
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1511,13 +1511,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.2457457796 1.0
- blocking 0.301983346 0.09303974078869968
- vectorization 0.3395954417 0.10462786205697575
- loop permutation 0.11965234119999998 0.0368643600962321
- array packing 0.1120537296 0.034523261280743095
- block caching 0.11104123460000001 0.03421131602416642
- parallelization 0.1445246564 0.044527411021639214
+ none 3.3862137396999996 1.0
+ blocking 0.3099287313 0.09152662977720302
+ vectorization 0.3463655988 0.10228698641766368
+ loop permutation 0.117646381 0.0347427510616689
+ array packing 0.10823761130000001 0.03196419943343248
+ block caching 0.11037158600000001 0.03259439435437951
+ parallelization 0.1443010019 0.042614262711244064
@@ -1552,6 +1552,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 0.772 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index e54fae090..425d09f80 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-fc8fdae61245c7a16a96cf031e36eaa58e3c0e49
+fe299d76882aa030851126cfbf32bf272492dc43
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index d05ebe16e..01a22c2c1 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -401,7 +401,7 @@
</div>
<img alt="../../_images/sphx_glr_from_mxnet_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_from_mxnet_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zipc559b520-d477-470f-a22c-4398d7b782e2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip6e7a2414-dad0-494e-b934-94211cb4012d 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 bd769dfed..20d07808e 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,49 +406,1997 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<07:42, 94.0kB/s]
- 0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
- 0%| | 72.0k/41.5M [00:00<04:59, 145kB/s]
- 0%| | 136k/41.5M [00:00<03:04, 235kB/s]
- 1%| | 272k/41.5M [00:00<01:38, 437kB/s]
- 1%|1 | 552k/41.5M [00:01<00:50, 845kB/s]
- 3%|2 | 1.09M/41.5M [00:01<00:25, 1.64MB/s]
- 4%|3 | 1.65M/41.5M [00:01<00:19, 2.19MB/s]
- 5%|5 | 2.22M/41.5M [00:01<00:16, 2.57MB/s]
- 7%|6 | 2.80M/41.5M [00:01<00:14, 2.84MB/s]
- 8%|8 | 3.40M/41.5M [00:01<00:12, 3.07MB/s]
- 10%|9 | 4.02M/41.5M [00:02<00:11, 3.28MB/s]
- 11%|#1 | 4.69M/41.5M [00:02<00:11, 3.49MB/s]
- 13%|#2 | 5.38M/41.5M [00:02<00:10, 3.69MB/s]
- 15%|#4 | 6.11M/41.5M [00:02<00:09, 3.89MB/s]
- 17%|#6 | 6.88M/41.5M [00:02<00:08, 4.10MB/s]
- 18%|#8 | 7.67M/41.5M [00:02<00:08, 4.30MB/s]
- 21%|## | 8.52M/41.5M [00:03<00:07, 4.52MB/s]
- 23%|##2 | 9.40M/41.5M [00:03<00:07, 4.75MB/s]
- 25%|##4 | 10.3M/41.5M [00:03<00:06, 4.99MB/s]
- 27%|##7 | 11.3M/41.5M [00:03<00:06, 5.25MB/s]
- 30%|##9 | 12.3M/41.5M [00:03<00:05, 5.51MB/s]
- 32%|###2 | 13.4M/41.5M [00:04<00:05, 5.79MB/s]
- 35%|###5 | 14.5M/41.5M [00:04<00:04, 6.07MB/s]
- 38%|###7 | 15.7M/41.5M [00:04<00:04, 6.38MB/s]
- 41%|#### | 17.0M/41.5M [00:04<00:03, 6.69MB/s]
- 44%|####4 | 18.3M/41.5M [00:04<00:03, 7.03MB/s]
- 47%|####7 | 19.6M/41.5M [00:04<00:03, 7.37MB/s]
- 51%|##### | 21.1M/41.5M [00:05<00:02, 7.74MB/s]
- 54%|#####4 | 22.6M/41.5M [00:05<00:02, 8.08MB/s]
- 58%|#####7 | 24.0M/41.5M [00:05<00:02, 8.32MB/s]
- 61%|######1 | 25.5M/41.5M [00:05<00:01, 8.48MB/s]
- 65%|######5 | 27.0M/41.5M [00:05<00:01, 8.59MB/s]
- 69%|######8 | 28.5M/41.5M [00:05<00:01, 8.64MB/s]
- 72%|#######2 | 29.9M/41.5M [00:06<00:01, 8.71MB/s]
- 76%|#######5 | 31.4M/41.5M [00:06<00:01, 8.76MB/s]
- 79%|#######9 | 32.9M/41.5M [00:06<00:01, 8.78MB/s]
- 83%|########2 | 34.4M/41.5M [00:06<00:00, 8.81MB/s]
- 86%|########6 | 35.9M/41.5M [00:06<00:00, 8.83MB/s]
- 90%|######### | 37.4M/41.5M [00:07<00:00, 8.84MB/s]
- 94%|#########3| 38.8M/41.5M [00:07<00:00, 8.85MB/s]
- 97%|#########7| 40.3M/41.5M [00:07<00:00, 8.84MB/s]
-100%|##########| 41.5M/41.5M [00:07<00:00, 5.90MB/s]
+ 0%| | 8.00k/41.5M [00:00<41:10, 17.6kB/s]
+ 0%| | 56.0k/41.5M [00:00<07:30, 96.3kB/s]
+ 0%| | 72.0k/41.5M [00:00<07:36, 95.1kB/s]
+ 0%| | 88.0k/41.5M [00:01<07:40, 94.2kB/s]
+ 0%| | 104k/41.5M [00:01<07:43, 93.6kB/s]
+ 0%| | 120k/41.5M [00:01<07:45, 93.2kB/s]
+ 0%| | 136k/41.5M [00:01<10:07, 71.4kB/s]
+ 0%| | 160k/41.5M [00:01<08:12, 88.0kB/s]
+ 0%| | 176k/41.5M [00:02<10:13, 70.6kB/s]
+ 0%| | 200k/41.5M [00:02<12:12, 59.1kB/s]
+ 1%| | 232k/41.5M [00:03<08:47, 82.1kB/s]
+ 1%| | 248k/41.5M [00:03<10:20, 69.7kB/s]
+ 1%| | 264k/41.5M [00:03<09:43, 74.2kB/s]
+ 1%| | 280k/41.5M [00:03<09:13, 78.1kB/s]
+ 1%| | 296k/41.5M [00:03<08:50, 81.5kB/s]
+ 1%| | 312k/41.5M [00:04<08:32, 84.2kB/s]
+ 1%| | 328k/41.5M [00:04<10:33, 68.2kB/s]
+ 1%| | 344k/41.5M [00:04<09:45, 73.7kB/s]
+ 1%| | 360k/41.5M [00:04<11:27, 62.8kB/s]
+ 1%| | 384k/41.5M [00:05<09:02, 79.5kB/s]
+ 1%| | 400k/41.5M [00:05<08:42, 82.5kB/s]
+ 1%| | 416k/41.5M [00:05<08:26, 85.0kB/s]
+ 1%|1 | 432k/41.5M [00:05<10:27, 68.6kB/s]
+ 1%|1 | 448k/41.5M [00:06<09:41, 74.1kB/s]
+ 1%|1 | 464k/41.5M [00:06<09:07, 78.6kB/s]
+ 1%|1 | 480k/41.5M [00:06<08:43, 82.2kB/s]
+ 1%|1 | 496k/41.5M [00:06<10:44, 66.7kB/s]
+ 1%|1 | 520k/41.5M [00:06<08:34, 83.5kB/s]
+ 1%|1 | 536k/41.5M [00:07<08:21, 85.7kB/s]
+ 1%|1 | 552k/41.5M [00:07<10:20, 69.2kB/s]
+ 1%|1 | 568k/41.5M [00:07<09:36, 74.5kB/s]
+ 1%|1 | 584k/41.5M [00:07<09:03, 78.9kB/s]
+ 1%|1 | 600k/41.5M [00:07<08:40, 82.4kB/s]
+ 1%|1 | 616k/41.5M [00:08<08:24, 85.1kB/s]
+ 1%|1 | 632k/41.5M [00:08<10:29, 68.0kB/s]
+ 2%|1 | 648k/41.5M [00:08<09:40, 73.8kB/s]
+ 2%|1 | 656k/41.5M [00:08<10:41, 66.8kB/s]
+ 2%|1 | 672k/41.5M [00:09<09:42, 73.6kB/s]
+ 2%|1 | 688k/41.5M [00:09<09:03, 78.7kB/s]
+ 2%|1 | 696k/41.5M [00:09<10:15, 69.5kB/s]
+ 2%|1 | 712k/41.5M [00:09<12:04, 59.1kB/s]
+ 2%|1 | 736k/41.5M [00:09<09:06, 78.2kB/s]
+ 2%|1 | 752k/41.5M [00:10<09:14, 77.1kB/s]
+ 2%|1 | 768k/41.5M [00:10<10:30, 67.8kB/s]
+ 2%|1 | 784k/41.5M [00:10<09:40, 73.5kB/s]
+ 2%|1 | 792k/41.5M [00:10<10:40, 66.6kB/s]
+ 2%|1 | 808k/41.5M [00:11<09:41, 73.4kB/s]
+ 2%|1 | 816k/41.5M [00:11<10:47, 65.9kB/s]
+ 2%|1 | 832k/41.5M [00:11<09:41, 73.3kB/s]
+ 2%|1 | 848k/41.5M [00:11<09:01, 78.8kB/s]
+ 2%|2 | 864k/41.5M [00:11<09:09, 77.6kB/s]
+ 2%|2 | 872k/41.5M [00:11<09:40, 73.4kB/s]
+ 2%|2 | 888k/41.5M [00:12<08:58, 79.1kB/s]
+ 2%|2 | 904k/41.5M [00:12<08:32, 83.0kB/s]
+ 2%|2 | 920k/41.5M [00:12<08:16, 85.8kB/s]
+ 2%|2 | 936k/41.5M [00:12<08:37, 82.1kB/s]
+ 2%|2 | 952k/41.5M [00:12<08:57, 79.2kB/s]
+ 2%|2 | 968k/41.5M [00:13<08:33, 82.8kB/s]
+ 2%|2 | 984k/41.5M [00:13<08:55, 79.4kB/s]
+ 2%|2 | 992k/41.5M [00:13<09:19, 75.9kB/s]
+ 2%|2 | 0.98M/41.5M [00:13<08:45, 80.8kB/s]
+ 2%|2 | 1.00M/41.5M [00:13<08:24, 84.2kB/s]
+ 2%|2 | 1.02M/41.5M [00:13<08:10, 86.6kB/s]
+ 2%|2 | 1.03M/41.5M [00:14<08:00, 88.3kB/s]
+ 3%|2 | 1.05M/41.5M [00:14<07:53, 89.5kB/s]
+ 3%|2 | 1.06M/41.5M [00:14<07:49, 90.3kB/s]
+ 3%|2 | 1.08M/41.5M [00:14<07:46, 90.9kB/s]
+ 3%|2 | 1.09M/41.5M [00:15<10:40, 66.1kB/s]
+ 3%|2 | 1.12M/41.5M [00:15<07:29, 94.1kB/s]
+ 3%|2 | 1.14M/41.5M [00:15<07:58, 88.5kB/s]
+ 3%|2 | 1.16M/41.5M [00:15<09:25, 74.8kB/s]
+ 3%|2 | 1.17M/41.5M [00:15<08:55, 78.9kB/s]
+ 3%|2 | 1.19M/41.5M [00:16<08:33, 82.2kB/s]
+ 3%|2 | 1.20M/41.5M [00:16<08:47, 80.0kB/s]
+ 3%|2 | 1.22M/41.5M [00:16<08:27, 83.2kB/s]
+ 3%|2 | 1.23M/41.5M [00:16<09:55, 70.9kB/s]
+ 3%|3 | 1.25M/41.5M [00:17<09:14, 76.1kB/s]
+ 3%|3 | 1.27M/41.5M [00:17<08:45, 80.2kB/s]
+ 3%|3 | 1.28M/41.5M [00:17<08:25, 83.5kB/s]
+ 3%|3 | 1.30M/41.5M [00:17<08:10, 85.9kB/s]
+ 3%|3 | 1.31M/41.5M [00:17<08:00, 87.7kB/s]
+ 3%|3 | 1.33M/41.5M [00:17<07:53, 89.0kB/s]
+ 3%|3 | 1.34M/41.5M [00:18<07:47, 90.0kB/s]
+ 3%|3 | 1.36M/41.5M [00:18<07:44, 90.7kB/s]
+ 3%|3 | 1.38M/41.5M [00:18<06:41, 105kB/s]
+ 3%|3 | 1.40M/41.5M [00:18<06:56, 101kB/s]
+ 3%|3 | 1.41M/41.5M [00:18<07:07, 98.4kB/s]
+ 3%|3 | 1.43M/41.5M [00:18<07:15, 96.6kB/s]
+ 3%|3 | 1.45M/41.5M [00:19<07:20, 95.3kB/s]
+ 4%|3 | 1.46M/41.5M [00:19<07:24, 94.4kB/s]
+ 4%|3 | 1.48M/41.5M [00:19<07:27, 93.7kB/s]
+ 4%|3 | 1.50M/41.5M [00:19<06:31, 107kB/s]
+ 4%|3 | 1.52M/41.5M [00:19<06:48, 103kB/s]
+ 4%|3 | 1.53M/41.5M [00:20<07:00, 99.6kB/s]
+ 4%|3 | 1.55M/41.5M [00:20<07:40, 90.9kB/s]
+ 4%|3 | 1.57M/41.5M [00:20<06:14, 112kB/s]
+ 4%|3 | 1.59M/41.5M [00:20<06:35, 106kB/s]
+ 4%|3 | 1.60M/41.5M [00:20<06:51, 102kB/s]
+ 4%|3 | 1.62M/41.5M [00:20<07:02, 98.9kB/s]
+ 4%|3 | 1.63M/41.5M [00:21<07:11, 96.9kB/s]
+ 4%|3 | 1.65M/41.5M [00:21<07:17, 95.5kB/s]
+ 4%|4 | 1.67M/41.5M [00:21<06:25, 108kB/s]
+ 4%|4 | 1.69M/41.5M [00:21<06:42, 104kB/s]
+ 4%|4 | 1.71M/41.5M [00:21<06:06, 114kB/s]
+ 4%|4 | 1.73M/41.5M [00:21<06:28, 107kB/s]
+ 4%|4 | 1.75M/41.5M [00:22<05:56, 117kB/s]
+ 4%|4 | 1.77M/41.5M [00:22<05:38, 123kB/s]
+ 4%|4 | 1.80M/41.5M [00:22<05:25, 128kB/s]
+ 4%|4 | 1.81M/41.5M [00:22<05:55, 117kB/s]
+ 4%|4 | 1.84M/41.5M [00:22<05:36, 124kB/s]
+ 4%|4 | 1.85M/41.5M [00:23<06:30, 106kB/s]
+ 5%|4 | 1.88M/41.5M [00:23<05:35, 124kB/s]
+ 5%|4 | 1.89M/41.5M [00:23<06:03, 114kB/s]
+ 5%|4 | 1.91M/41.5M [00:23<06:25, 108kB/s]
+ 5%|4 | 1.93M/41.5M [00:23<05:54, 117kB/s]
+ 5%|4 | 1.95M/41.5M [00:23<06:18, 109kB/s]
+ 5%|4 | 1.97M/41.5M [00:24<05:50, 118kB/s]
+ 5%|4 | 1.99M/41.5M [00:24<05:33, 124kB/s]
+ 5%|4 | 2.01M/41.5M [00:24<06:01, 115kB/s]
+ 5%|4 | 2.02M/41.5M [00:24<07:17, 94.7kB/s]
+ 5%|4 | 2.05M/41.5M [00:24<05:46, 119kB/s]
+ 5%|4 | 2.07M/41.5M [00:25<06:10, 112kB/s]
+ 5%|5 | 2.09M/41.5M [00:25<05:46, 119kB/s]
+ 5%|5 | 2.11M/41.5M [00:25<06:10, 112kB/s]
+ 5%|5 | 2.13M/41.5M [00:25<05:45, 119kB/s]
+ 5%|5 | 2.15M/41.5M [00:25<06:10, 111kB/s]
+ 5%|5 | 2.17M/41.5M [00:25<05:45, 119kB/s]
+ 5%|5 | 2.20M/41.5M [00:26<05:29, 125kB/s]
+ 5%|5 | 2.22M/41.5M [00:26<05:19, 129kB/s]
+ 5%|5 | 2.24M/41.5M [00:26<05:12, 132kB/s]
+ 5%|5 | 2.26M/41.5M [00:26<05:42, 120kB/s]
+ 5%|5 | 2.28M/41.5M [00:26<05:27, 126kB/s]
+ 6%|5 | 2.30M/41.5M [00:27<06:52, 99.5kB/s]
+ 6%|5 | 2.34M/41.5M [00:27<05:11, 132kB/s]
+ 6%|5 | 2.36M/41.5M [00:27<05:37, 122kB/s]
+ 6%|5 | 2.38M/41.5M [00:27<06:00, 114kB/s]
+ 6%|5 | 2.39M/41.5M [00:27<06:20, 108kB/s]
+ 6%|5 | 2.41M/41.5M [00:28<05:51, 116kB/s]
+ 6%|5 | 2.44M/41.5M [00:28<05:33, 123kB/s]
+ 6%|5 | 2.46M/41.5M [00:28<05:21, 127kB/s]
+ 6%|5 | 2.48M/41.5M [00:28<05:49, 117kB/s]
+ 6%|6 | 2.50M/41.5M [00:28<05:31, 123kB/s]
+ 6%|6 | 2.52M/41.5M [00:28<05:19, 128kB/s]
+ 6%|6 | 2.55M/41.5M [00:29<05:11, 131kB/s]
+ 6%|6 | 2.57M/41.5M [00:29<05:06, 133kB/s]
+ 6%|6 | 2.59M/41.5M [00:29<05:02, 135kB/s]
+ 6%|6 | 2.62M/41.5M [00:29<05:00, 136kB/s]
+ 6%|6 | 2.63M/41.5M [00:29<06:18, 108kB/s]
+ 6%|6 | 2.66M/41.5M [00:30<05:16, 129kB/s]
+ 6%|6 | 2.69M/41.5M [00:30<05:17, 128kB/s]
+ 7%|6 | 2.70M/41.5M [00:30<05:35, 121kB/s]
+ 7%|6 | 2.73M/41.5M [00:30<07:26, 91.0kB/s]
+ 7%|6 | 2.76M/41.5M [00:31<05:34, 122kB/s]
+ 7%|6 | 2.77M/41.5M [00:31<05:56, 114kB/s]
+ 7%|6 | 2.79M/41.5M [00:31<06:15, 108kB/s]
+ 7%|6 | 2.81M/41.5M [00:31<05:56, 114kB/s]
+ 7%|6 | 2.83M/41.5M [00:31<06:16, 108kB/s]
+ 7%|6 | 2.84M/41.5M [00:31<06:22, 106kB/s]
+ 7%|6 | 2.86M/41.5M [00:32<06:09, 110kB/s]
+ 7%|6 | 2.88M/41.5M [00:32<06:00, 112kB/s]
+ 7%|6 | 2.89M/41.5M [00:32<06:22, 106kB/s]
+ 7%|7 | 2.91M/41.5M [00:32<06:38, 101kB/s]
+ 7%|7 | 2.93M/41.5M [00:32<05:57, 113kB/s]
+ 7%|7 | 2.95M/41.5M [00:32<05:34, 121kB/s]
+ 7%|7 | 2.98M/41.5M [00:33<05:20, 126kB/s]
+ 7%|7 | 3.00M/41.5M [00:33<05:10, 130kB/s]
+ 7%|7 | 3.02M/41.5M [00:33<06:36, 102kB/s]
+ 7%|7 | 3.06M/41.5M [00:33<05:36, 120kB/s]
+ 7%|7 | 3.08M/41.5M [00:34<06:41, 100kB/s]
+ 7%|7 | 3.11M/41.5M [00:34<06:13, 108kB/s]
+ 8%|7 | 3.12M/41.5M [00:34<06:25, 104kB/s]
+ 8%|7 | 3.14M/41.5M [00:34<06:36, 101kB/s]
+ 8%|7 | 3.16M/41.5M [00:34<06:54, 96.9kB/s]
+ 8%|7 | 3.17M/41.5M [00:35<06:51, 97.6kB/s]
+ 8%|7 | 3.19M/41.5M [00:35<08:55, 75.0kB/s]
+ 8%|7 | 3.20M/41.5M [00:35<08:27, 79.1kB/s]
+ 8%|7 | 3.22M/41.5M [00:35<08:06, 82.5kB/s]
+ 8%|7 | 3.23M/41.5M [00:36<08:30, 78.5kB/s]
+ 8%|7 | 3.25M/41.5M [00:36<07:29, 89.2kB/s]
+ 8%|7 | 3.27M/41.5M [00:36<09:32, 70.0kB/s]
+ 8%|7 | 3.28M/41.5M [00:36<08:51, 75.4kB/s]
+ 8%|7 | 3.30M/41.5M [00:36<08:22, 79.7kB/s]
+ 8%|7 | 3.31M/41.5M [00:37<08:01, 83.1kB/s]
+ 8%|8 | 3.33M/41.5M [00:37<07:47, 85.6kB/s]
+ 8%|8 | 3.34M/41.5M [00:37<07:37, 87.5kB/s]
+ 8%|8 | 3.36M/41.5M [00:37<07:29, 88.9kB/s]
+ 8%|8 | 3.38M/41.5M [00:37<07:24, 89.9kB/s]
+ 8%|8 | 3.39M/41.5M [00:37<07:21, 90.6kB/s]
+ 8%|8 | 3.41M/41.5M [00:38<06:22, 104kB/s]
+ 8%|8 | 3.42M/41.5M [00:38<06:03, 110kB/s]
+ 8%|8 | 3.44M/41.5M [00:38<06:24, 104kB/s]
+ 8%|8 | 3.45M/41.5M [00:38<06:37, 100kB/s]
+ 8%|8 | 3.47M/41.5M [00:38<06:47, 97.8kB/s]
+ 8%|8 | 3.48M/41.5M [00:38<06:15, 106kB/s]
+ 8%|8 | 3.51M/41.5M [00:39<06:15, 106kB/s]
+ 9%|8 | 3.53M/41.5M [00:39<05:43, 116kB/s]
+ 9%|8 | 3.55M/41.5M [00:39<05:24, 123kB/s]
+ 9%|8 | 3.57M/41.5M [00:39<05:18, 125kB/s]
+ 9%|8 | 3.59M/41.5M [00:39<05:07, 129kB/s]
+ 9%|8 | 3.62M/41.5M [00:40<07:04, 93.7kB/s]
+ 9%|8 | 3.66M/41.5M [00:40<04:26, 149kB/s]
+ 9%|8 | 3.69M/41.5M [00:40<04:53, 135kB/s]
+ 9%|8 | 3.71M/41.5M [00:40<04:51, 136kB/s]
+ 9%|8 | 3.73M/41.5M [00:40<04:53, 135kB/s]
+ 9%|9 | 3.74M/41.5M [00:40<05:23, 122kB/s]
+ 9%|9 | 3.77M/41.5M [00:41<06:29, 101kB/s]
+ 9%|9 | 3.79M/41.5M [00:41<06:10, 107kB/s]
+ 9%|9 | 3.83M/41.5M [00:41<06:20, 104kB/s]
+ 9%|9 | 3.87M/41.5M [00:42<04:40, 141kB/s]
+ 9%|9 | 3.89M/41.5M [00:42<07:02, 93.2kB/s]
+ 9%|9 | 3.92M/41.5M [00:42<05:55, 111kB/s]
+ 9%|9 | 3.94M/41.5M [00:43<07:28, 87.7kB/s]
+ 10%|9 | 3.95M/41.5M [00:43<07:23, 88.7kB/s]
+ 10%|9 | 3.97M/41.5M [00:43<07:19, 89.5kB/s]
+ 10%|9 | 3.98M/41.5M [00:43<07:16, 90.0kB/s]
+ 10%|9 | 4.00M/41.5M [00:44<12:48, 51.1kB/s]
+ 10%|9 | 4.04M/41.5M [00:44<07:59, 81.9kB/s]
+ 10%|9 | 4.05M/41.5M [00:44<08:36, 76.0kB/s]
+ 10%|9 | 4.07M/41.5M [00:44<08:14, 79.3kB/s]
+ 10%|9 | 4.09M/41.5M [00:45<08:47, 74.4kB/s]
+ 10%|9 | 4.10M/41.5M [00:45<08:19, 78.4kB/s]
+ 10%|9 | 4.12M/41.5M [00:45<07:59, 81.8kB/s]
+ 10%|9 | 4.13M/41.5M [00:45<07:43, 84.4kB/s]
+ 10%|9 | 4.15M/41.5M [00:45<07:32, 86.5kB/s]
+ 10%|# | 4.16M/41.5M [00:46<09:27, 69.0kB/s]
+ 10%|# | 4.19M/41.5M [00:46<07:37, 85.4kB/s]
+ 10%|# | 4.20M/41.5M [00:46<09:22, 69.6kB/s]
+ 10%|# | 4.22M/41.5M [00:47<08:43, 74.6kB/s]
+ 10%|# | 4.23M/41.5M [00:47<08:15, 78.9kB/s]
+ 10%|# | 4.25M/41.5M [00:47<07:54, 82.3kB/s]
+ 10%|# | 4.27M/41.5M [00:47<07:39, 85.0kB/s]
+ 10%|# | 4.28M/41.5M [00:47<07:28, 87.0kB/s]
+ 10%|# | 4.30M/41.5M [00:47<07:20, 88.5kB/s]
+ 10%|# | 4.31M/41.5M [00:48<07:15, 89.5kB/s]
+ 10%|# | 4.33M/41.5M [00:48<07:11, 90.3kB/s]
+ 10%|# | 4.34M/41.5M [00:48<07:08, 90.9kB/s]
+ 11%|# | 4.36M/41.5M [00:48<07:51, 82.5kB/s]
+ 11%|# | 4.38M/41.5M [00:48<06:52, 94.4kB/s]
+ 11%|# | 4.39M/41.5M [00:48<06:55, 93.7kB/s]
+ 11%|# | 4.41M/41.5M [00:49<06:56, 93.3kB/s]
+ 11%|# | 4.42M/41.5M [00:49<06:58, 93.0kB/s]
+ 11%|# | 4.44M/41.5M [00:49<06:58, 92.8kB/s]
+ 11%|# | 4.45M/41.5M [00:49<06:59, 92.6kB/s]
+ 11%|# | 4.47M/41.5M [00:49<08:13, 78.7kB/s]
+ 11%|# | 4.49M/41.5M [00:50<07:15, 89.1kB/s]
+ 11%|# | 4.51M/41.5M [00:50<07:11, 89.9kB/s]
+ 11%|# | 4.52M/41.5M [00:50<07:30, 86.1kB/s]
+ 11%|# | 4.54M/41.5M [00:50<06:58, 92.6kB/s]
+ 11%|# | 4.55M/41.5M [00:50<06:58, 92.5kB/s]
+ 11%|#1 | 4.57M/41.5M [00:51<06:44, 95.7kB/s]
+ 11%|#1 | 4.59M/41.5M [00:51<06:17, 102kB/s]
+ 11%|#1 | 4.61M/41.5M [00:51<06:19, 102kB/s]
+ 11%|#1 | 4.62M/41.5M [00:51<06:16, 103kB/s]
+ 11%|#1 | 4.64M/41.5M [00:51<05:58, 108kB/s]
+ 11%|#1 | 4.66M/41.5M [00:51<06:07, 105kB/s]
+ 11%|#1 | 4.68M/41.5M [00:52<05:40, 113kB/s]
+ 11%|#1 | 4.70M/41.5M [00:52<05:55, 109kB/s]
+ 11%|#1 | 4.72M/41.5M [00:52<05:31, 116kB/s]
+ 11%|#1 | 4.74M/41.5M [00:52<05:12, 123kB/s]
+ 11%|#1 | 4.77M/41.5M [00:52<05:35, 115kB/s]
+ 12%|#1 | 4.79M/41.5M [00:53<05:16, 121kB/s]
+ 12%|#1 | 4.81M/41.5M [00:53<05:04, 126kB/s]
+ 12%|#1 | 4.84M/41.5M [00:53<04:55, 130kB/s]
+ 12%|#1 | 4.86M/41.5M [00:53<04:18, 149kB/s]
+ 12%|#1 | 4.88M/41.5M [00:53<04:24, 145kB/s]
+ 12%|#1 | 4.91M/41.5M [00:53<04:11, 153kB/s]
+ 12%|#1 | 4.92M/41.5M [00:53<04:25, 145kB/s]
+ 12%|#1 | 4.94M/41.5M [00:54<04:42, 136kB/s]
+ 12%|#1 | 4.97M/41.5M [00:54<04:11, 152kB/s]
+ 12%|#2 | 4.99M/41.5M [00:54<04:19, 148kB/s]
+ 12%|#2 | 5.02M/41.5M [00:54<04:00, 159kB/s]
+ 12%|#2 | 5.05M/41.5M [00:54<03:41, 173kB/s]
+ 12%|#2 | 5.08M/41.5M [00:54<03:36, 177kB/s]
+ 12%|#2 | 5.11M/41.5M [00:55<03:58, 160kB/s]
+ 12%|#2 | 5.14M/41.5M [00:55<03:23, 187kB/s]
+ 12%|#2 | 5.18M/41.5M [00:55<04:32, 140kB/s]
+ 13%|#2 | 5.22M/41.5M [00:55<04:06, 154kB/s]
+ 13%|#2 | 5.27M/41.5M [00:56<03:15, 194kB/s]
+ 13%|#2 | 5.29M/41.5M [00:56<03:11, 198kB/s]
+ 13%|#2 | 5.31M/41.5M [00:56<03:02, 208kB/s]
+ 13%|#2 | 5.34M/41.5M [00:56<03:25, 185kB/s]
+ 13%|#2 | 5.36M/41.5M [00:56<03:28, 181kB/s]
+ 13%|#2 | 5.38M/41.5M [00:56<05:01, 126kB/s]
+ 13%|#3 | 5.44M/41.5M [00:57<03:13, 196kB/s]
+ 13%|#3 | 5.47M/41.5M [00:57<03:16, 193kB/s]
+ 13%|#3 | 5.49M/41.5M [00:57<03:33, 177kB/s]
+ 13%|#3 | 5.52M/41.5M [00:57<03:48, 165kB/s]
+ 13%|#3 | 5.54M/41.5M [00:57<03:28, 181kB/s]
+ 13%|#3 | 5.56M/41.5M [00:57<03:45, 167kB/s]
+ 13%|#3 | 5.59M/41.5M [00:58<03:38, 172kB/s]
+ 14%|#3 | 5.62M/41.5M [00:58<03:28, 180kB/s]
+ 14%|#3 | 5.64M/41.5M [00:58<03:28, 181kB/s]
+ 14%|#3 | 5.66M/41.5M [00:58<03:46, 166kB/s]
+ 14%|#3 | 5.69M/41.5M [00:58<03:58, 157kB/s]
+ 14%|#3 | 5.71M/41.5M [00:58<03:33, 175kB/s]
+ 14%|#3 | 5.74M/41.5M [00:58<03:29, 179kB/s]
+ 14%|#3 | 5.77M/41.5M [00:59<05:01, 124kB/s]
+ 14%|#4 | 5.82M/41.5M [00:59<03:14, 193kB/s]
+ 14%|#4 | 5.85M/41.5M [00:59<04:57, 126kB/s]
+ 14%|#4 | 5.89M/41.5M [01:00<04:11, 148kB/s]
+ 14%|#4 | 5.91M/41.5M [01:00<04:15, 146kB/s]
+ 14%|#4 | 5.94M/41.5M [01:00<04:18, 144kB/s]
+ 14%|#4 | 5.96M/41.5M [01:00<06:39, 93.2kB/s]
+ 14%|#4 | 5.98M/41.5M [01:01<06:22, 97.5kB/s]
+ 14%|#4 | 6.02M/41.5M [01:01<05:04, 122kB/s]
+ 15%|#4 | 6.03M/41.5M [01:01<05:23, 115kB/s]
+ 15%|#4 | 6.05M/41.5M [01:01<05:40, 109kB/s]
+ 15%|#4 | 6.06M/41.5M [01:01<05:55, 105kB/s]
+ 15%|#4 | 6.09M/41.5M [01:02<05:25, 114kB/s]
+ 15%|#4 | 6.10M/41.5M [01:02<05:44, 108kB/s]
+ 15%|#4 | 6.12M/41.5M [01:02<05:17, 117kB/s]
+ 15%|#4 | 6.15M/41.5M [01:02<05:01, 123kB/s]
+ 15%|#4 | 6.17M/41.5M [01:02<04:50, 127kB/s]
+ 15%|#4 | 6.20M/41.5M [01:02<04:43, 131kB/s]
+ 15%|#4 | 6.21M/41.5M [01:03<05:09, 119kB/s]
+ 15%|#5 | 6.23M/41.5M [01:03<05:32, 111kB/s]
+ 15%|#5 | 6.25M/41.5M [01:03<05:09, 119kB/s]
+ 15%|#5 | 6.27M/41.5M [01:03<05:32, 111kB/s]
+ 15%|#5 | 6.29M/41.5M [01:03<05:09, 119kB/s]
+ 15%|#5 | 6.30M/41.5M [01:03<05:31, 111kB/s]
+ 15%|#5 | 6.33M/41.5M [01:04<06:42, 91.7kB/s]
+ 15%|#5 | 6.36M/41.5M [01:04<05:21, 115kB/s]
+ 15%|#5 | 6.38M/41.5M [01:04<05:38, 109kB/s]
+ 15%|#5 | 6.39M/41.5M [01:04<05:52, 104kB/s]
+ 15%|#5 | 6.41M/41.5M [01:05<07:46, 78.9kB/s]
+ 16%|#5 | 6.45M/41.5M [01:05<05:19, 115kB/s]
+ 16%|#5 | 6.46M/41.5M [01:05<05:36, 109kB/s]
+ 16%|#5 | 6.48M/41.5M [01:05<05:50, 105kB/s]
+ 16%|#5 | 6.49M/41.5M [01:05<06:02, 101kB/s]
+ 16%|#5 | 6.51M/41.5M [01:06<06:11, 98.7kB/s]
+ 16%|#5 | 6.52M/41.5M [01:06<06:18, 96.9kB/s]
+ 16%|#5 | 6.54M/41.5M [01:06<06:23, 95.5kB/s]
+ 16%|#5 | 6.55M/41.5M [01:06<06:27, 94.6kB/s]
+ 16%|#5 | 6.58M/41.5M [01:06<05:40, 108kB/s]
+ 16%|#5 | 6.59M/41.5M [01:07<05:55, 103kB/s]
+ 16%|#5 | 6.61M/41.5M [01:07<05:34, 109kB/s]
+ 16%|#5 | 6.63M/41.5M [01:07<07:15, 83.9kB/s]
+ 16%|#6 | 6.67M/41.5M [01:07<05:05, 120kB/s]
+ 16%|#6 | 6.69M/41.5M [01:07<05:24, 113kB/s]
+ 16%|#6 | 6.70M/41.5M [01:08<07:12, 84.3kB/s]
+ 16%|#6 | 6.73M/41.5M [01:08<06:12, 97.9kB/s]
+ 16%|#6 | 6.74M/41.5M [01:08<06:21, 95.4kB/s]
+ 16%|#6 | 6.76M/41.5M [01:08<06:25, 94.6kB/s]
+ 16%|#6 | 6.77M/41.5M [01:09<07:03, 85.9kB/s]
+ 16%|#6 | 6.79M/41.5M [01:09<06:55, 87.5kB/s]
+ 16%|#6 | 6.80M/41.5M [01:09<06:49, 88.8kB/s]
+ 16%|#6 | 6.82M/41.5M [01:09<06:44, 89.8kB/s]
+ 16%|#6 | 6.84M/41.5M [01:09<08:23, 72.2kB/s]
+ 17%|#6 | 6.85M/41.5M [01:10<07:19, 82.7kB/s]
+ 17%|#6 | 6.87M/41.5M [01:10<07:05, 85.3kB/s]
+ 17%|#6 | 6.88M/41.5M [01:10<07:00, 86.2kB/s]
+ 17%|#6 | 6.90M/41.5M [01:10<06:52, 87.9kB/s]
+ 17%|#6 | 6.91M/41.5M [01:10<06:41, 90.3kB/s]
+ 17%|#6 | 6.93M/41.5M [01:10<06:38, 90.8kB/s]
+ 17%|#6 | 6.95M/41.5M [01:11<05:50, 103kB/s]
+ 17%|#6 | 6.97M/41.5M [01:11<06:00, 100kB/s]
+ 17%|#6 | 6.98M/41.5M [01:11<06:09, 97.9kB/s]
+ 17%|#6 | 7.00M/41.5M [01:11<06:10, 97.5kB/s]
+ 17%|#6 | 7.02M/41.5M [01:11<05:38, 107kB/s]
+ 17%|#6 | 7.03M/41.5M [01:12<08:33, 70.3kB/s]
+ 17%|#6 | 7.05M/41.5M [01:12<07:12, 83.5kB/s]
+ 17%|#7 | 7.08M/41.5M [01:12<05:23, 111kB/s]
+ 17%|#7 | 7.09M/41.5M [01:12<05:40, 106kB/s]
+ 17%|#7 | 7.11M/41.5M [01:12<05:53, 102kB/s]
+ 17%|#7 | 7.12M/41.5M [01:12<06:03, 99.2kB/s]
+ 17%|#7 | 7.14M/41.5M [01:13<08:25, 71.2kB/s]
+ 17%|#7 | 7.18M/41.5M [01:13<05:12, 115kB/s]
+ 17%|#7 | 7.20M/41.5M [01:13<05:52, 102kB/s]
+ 17%|#7 | 7.21M/41.5M [01:13<05:36, 107kB/s]
+ 17%|#7 | 7.23M/41.5M [01:14<05:49, 103kB/s]
+ 17%|#7 | 7.24M/41.5M [01:14<06:00, 99.7kB/s]
+ 17%|#7 | 7.26M/41.5M [01:14<05:31, 108kB/s]
+ 18%|#7 | 7.27M/41.5M [01:14<05:18, 113kB/s]
+ 18%|#7 | 7.29M/41.5M [01:14<05:24, 111kB/s]
+ 18%|#7 | 7.30M/41.5M [01:14<07:06, 84.0kB/s]
+ 18%|#7 | 7.34M/41.5M [01:15<05:55, 101kB/s]
+ 18%|#7 | 7.35M/41.5M [01:15<06:03, 98.5kB/s]
+ 18%|#7 | 7.37M/41.5M [01:15<06:09, 96.8kB/s]
+ 18%|#7 | 7.39M/41.5M [01:15<05:29, 108kB/s]
+ 18%|#7 | 7.41M/41.5M [01:15<05:44, 104kB/s]
+ 18%|#7 | 7.42M/41.5M [01:15<05:14, 113kB/s]
+ 18%|#7 | 7.44M/41.5M [01:16<04:58, 120kB/s]
+ 18%|#7 | 7.45M/41.5M [01:16<05:23, 110kB/s]
+ 18%|#8 | 7.47M/41.5M [01:16<07:31, 79.1kB/s]
+ 18%|#8 | 7.50M/41.5M [01:16<05:13, 114kB/s]
+ 18%|#8 | 7.52M/41.5M [01:17<05:55, 100kB/s]
+ 18%|#8 | 7.53M/41.5M [01:17<06:03, 98.0kB/s]
+ 18%|#8 | 7.55M/41.5M [01:17<07:53, 75.1kB/s]
+ 18%|#8 | 7.58M/41.5M [01:17<05:29, 108kB/s]
+ 18%|#8 | 7.59M/41.5M [01:17<06:06, 97.0kB/s]
+ 18%|#8 | 7.61M/41.5M [01:18<06:32, 90.4kB/s]
+ 18%|#8 | 7.62M/41.5M [01:18<06:30, 90.9kB/s]
+ 18%|#8 | 7.64M/41.5M [01:18<06:29, 91.2kB/s]
+ 18%|#8 | 7.66M/41.5M [01:18<06:27, 91.6kB/s]
+ 18%|#8 | 7.67M/41.5M [01:18<06:26, 91.8kB/s]
+ 19%|#8 | 7.69M/41.5M [01:18<06:25, 91.9kB/s]
+ 19%|#8 | 7.71M/41.5M [01:19<06:26, 91.7kB/s]
+ 19%|#8 | 7.73M/41.5M [01:19<05:40, 104kB/s]
+ 19%|#8 | 7.75M/41.5M [01:19<05:50, 101kB/s]
+ 19%|#8 | 7.77M/41.5M [01:19<07:41, 76.6kB/s]
+ 19%|#8 | 7.80M/41.5M [01:20<05:44, 102kB/s]
+ 19%|#8 | 7.82M/41.5M [01:20<05:16, 112kB/s]
+ 19%|#8 | 7.84M/41.5M [01:20<05:31, 106kB/s]
+ 19%|#8 | 7.85M/41.5M [01:20<05:43, 103kB/s]
+ 19%|#8 | 7.87M/41.5M [01:21<07:58, 73.7kB/s]
+ 19%|#9 | 7.90M/41.5M [01:21<08:19, 70.5kB/s]
+ 19%|#9 | 7.93M/41.5M [01:21<06:21, 92.1kB/s]
+ 19%|#9 | 7.95M/41.5M [01:21<06:21, 92.1kB/s]
+ 19%|#9 | 7.96M/41.5M [01:22<06:21, 92.2kB/s]
+ 19%|#9 | 7.98M/41.5M [01:22<09:31, 61.5kB/s]
+ 19%|#9 | 8.00M/41.5M [01:22<07:40, 76.3kB/s]
+ 19%|#9 | 8.02M/41.5M [01:23<07:20, 79.6kB/s]
+ 19%|#9 | 8.03M/41.5M [01:23<08:44, 66.9kB/s]
+ 19%|#9 | 8.05M/41.5M [01:23<08:04, 72.3kB/s]
+ 19%|#9 | 8.06M/41.5M [01:23<07:35, 77.0kB/s]
+ 19%|#9 | 8.08M/41.5M [01:23<07:13, 80.8kB/s]
+ 20%|#9 | 8.09M/41.5M [01:24<08:48, 66.3kB/s]
+ 20%|#9 | 8.12M/41.5M [01:24<07:02, 82.8kB/s]
+ 20%|#9 | 8.13M/41.5M [01:24<07:14, 80.5kB/s]
+ 20%|#9 | 8.15M/41.5M [01:24<08:19, 70.0kB/s]
+ 20%|#9 | 8.16M/41.5M [01:25<07:44, 75.2kB/s]
+ 20%|#9 | 8.18M/41.5M [01:25<07:19, 79.4kB/s]
+ 20%|#9 | 8.20M/41.5M [01:25<07:01, 82.8kB/s]
+ 20%|#9 | 8.21M/41.5M [01:25<07:14, 80.3kB/s]
+ 20%|#9 | 8.23M/41.5M [01:25<06:57, 83.5kB/s]
+ 20%|#9 | 8.24M/41.5M [01:26<06:45, 85.9kB/s]
+ 20%|#9 | 8.26M/41.5M [01:26<06:37, 87.7kB/s]
+ 20%|#9 | 8.27M/41.5M [01:26<06:31, 89.0kB/s]
+ 20%|#9 | 8.29M/41.5M [01:26<06:26, 90.0kB/s]
+ 20%|## | 8.30M/41.5M [01:26<06:23, 90.6kB/s]
+ 20%|## | 8.32M/41.5M [01:26<06:21, 91.1kB/s]
+ 20%|## | 8.34M/41.5M [01:27<05:54, 98.2kB/s]
+ 20%|## | 8.35M/41.5M [01:27<06:00, 96.3kB/s]
+ 20%|## | 8.37M/41.5M [01:27<06:05, 95.1kB/s]
+ 20%|## | 8.38M/41.5M [01:27<08:02, 72.0kB/s]
+ 20%|## | 8.42M/41.5M [01:27<05:10, 112kB/s]
+ 20%|## | 8.44M/41.5M [01:28<05:25, 107kB/s]
+ 20%|## | 8.46M/41.5M [01:28<05:19, 108kB/s]
+ 20%|## | 8.48M/41.5M [01:28<07:02, 81.9kB/s]
+ 21%|## | 8.52M/41.5M [01:28<04:56, 117kB/s]
+ 21%|## | 8.53M/41.5M [01:29<05:12, 110kB/s]
+ 21%|## | 8.55M/41.5M [01:29<05:07, 112kB/s]
+ 21%|## | 8.56M/41.5M [01:29<05:23, 107kB/s]
+ 21%|## | 8.59M/41.5M [01:29<04:57, 116kB/s]
+ 21%|## | 8.60M/41.5M [01:29<05:16, 109kB/s]
+ 21%|## | 8.62M/41.5M [01:29<04:52, 118kB/s]
+ 21%|## | 8.65M/41.5M [01:30<04:38, 124kB/s]
+ 21%|## | 8.67M/41.5M [01:30<04:28, 128kB/s]
+ 21%|## | 8.69M/41.5M [01:30<06:20, 90.4kB/s]
+ 21%|##1 | 8.73M/41.5M [01:30<04:50, 118kB/s]
+ 21%|##1 | 8.74M/41.5M [01:31<05:07, 112kB/s]
+ 21%|##1 | 8.76M/41.5M [01:31<05:02, 114kB/s]
+ 21%|##1 | 8.78M/41.5M [01:31<05:03, 113kB/s]
+ 21%|##1 | 8.80M/41.5M [01:31<04:58, 115kB/s]
+ 21%|##1 | 8.81M/41.5M [01:31<06:51, 83.2kB/s]
+ 21%|##1 | 8.85M/41.5M [01:32<05:02, 113kB/s]
+ 21%|##1 | 8.87M/41.5M [01:32<05:17, 108kB/s]
+ 21%|##1 | 8.89M/41.5M [01:32<04:55, 116kB/s]
+ 21%|##1 | 8.91M/41.5M [01:32<04:58, 114kB/s]
+ 22%|##1 | 8.93M/41.5M [01:32<04:54, 116kB/s]
+ 22%|##1 | 8.95M/41.5M [01:32<04:38, 122kB/s]
+ 22%|##1 | 8.98M/41.5M [01:33<04:46, 119kB/s]
+ 22%|##1 | 8.99M/41.5M [01:33<06:32, 86.8kB/s]
+ 22%|##1 | 9.03M/41.5M [01:33<04:40, 121kB/s]
+ 22%|##1 | 9.05M/41.5M [01:34<05:57, 95.2kB/s]
+ 22%|##1 | 9.07M/41.5M [01:34<05:40, 99.7kB/s]
+ 22%|##1 | 9.09M/41.5M [01:34<05:46, 97.9kB/s]
+ 22%|##1 | 9.10M/41.5M [01:34<05:51, 96.5kB/s]
+ 22%|##1 | 9.12M/41.5M [01:34<05:55, 95.4kB/s]
+ 22%|##2 | 9.13M/41.5M [01:34<05:59, 94.5kB/s]
+ 22%|##2 | 9.15M/41.5M [01:35<06:01, 93.9kB/s]
+ 22%|##2 | 9.16M/41.5M [01:35<06:02, 93.4kB/s]
+ 22%|##2 | 9.18M/41.5M [01:35<06:04, 93.1kB/s]
+ 22%|##2 | 9.20M/41.5M [01:35<07:52, 71.6kB/s]
+ 22%|##2 | 9.20M/41.5M [01:36<09:14, 61.1kB/s]
+ 22%|##2 | 9.22M/41.5M [01:36<09:38, 58.5kB/s]
+ 22%|##2 | 9.25M/41.5M [01:36<06:52, 82.0kB/s]
+ 22%|##2 | 9.27M/41.5M [01:36<08:14, 68.3kB/s]
+ 22%|##2 | 9.27M/41.5M [01:37<08:51, 63.6kB/s]
+ 22%|##2 | 9.29M/41.5M [01:37<08:00, 70.3kB/s]
+ 22%|##2 | 9.30M/41.5M [01:37<08:45, 64.2kB/s]
+ 22%|##2 | 9.30M/41.5M [01:37<09:27, 59.5kB/s]
+ 22%|##2 | 9.32M/41.5M [01:37<08:12, 68.4kB/s]
+ 23%|##2 | 9.34M/41.5M [01:38<07:29, 75.1kB/s]
+ 23%|##2 | 9.34M/41.5M [01:38<08:24, 66.8kB/s]
+ 23%|##2 | 9.36M/41.5M [01:38<07:33, 74.2kB/s]
+ 23%|##2 | 9.38M/41.5M [01:38<09:08, 61.4kB/s]
+ 23%|##2 | 9.41M/41.5M [01:38<06:07, 91.5kB/s]
+ 23%|##2 | 9.42M/41.5M [01:39<06:30, 86.1kB/s]
+ 23%|##2 | 9.44M/41.5M [01:39<08:01, 69.7kB/s]
+ 23%|##2 | 9.45M/41.5M [01:39<07:04, 79.2kB/s]
+ 23%|##2 | 9.47M/41.5M [01:40<08:30, 65.8kB/s]
+ 23%|##2 | 9.48M/41.5M [01:40<09:07, 61.3kB/s]
+ 23%|##2 | 9.49M/41.5M [01:40<08:07, 68.8kB/s]
+ 23%|##2 | 9.50M/41.5M [01:40<08:52, 63.0kB/s]
+ 23%|##2 | 9.52M/41.5M [01:40<07:53, 70.9kB/s]
+ 23%|##2 | 9.53M/41.5M [01:40<07:16, 76.8kB/s]
+ 23%|##3 | 9.55M/41.5M [01:41<06:52, 81.2kB/s]
+ 23%|##3 | 9.56M/41.5M [01:41<06:36, 84.4kB/s]
+ 23%|##3 | 9.58M/41.5M [01:41<06:25, 86.7kB/s]
+ 23%|##3 | 9.59M/41.5M [01:41<06:18, 88.3kB/s]
+ 23%|##3 | 9.61M/41.5M [01:41<06:13, 89.5kB/s]
+ 23%|##3 | 9.62M/41.5M [01:42<08:00, 69.5kB/s]
+ 23%|##3 | 9.66M/41.5M [01:42<05:41, 97.9kB/s]
+ 23%|##3 | 9.67M/41.5M [01:42<05:46, 96.4kB/s]
+ 23%|##3 | 9.69M/41.5M [01:42<05:49, 95.3kB/s]
+ 23%|##3 | 9.70M/41.5M [01:42<05:52, 94.4kB/s]
+ 23%|##3 | 9.72M/41.5M [01:43<05:55, 93.8kB/s]
+ 23%|##3 | 9.73M/41.5M [01:43<05:56, 93.4kB/s]
+ 24%|##3 | 9.76M/41.5M [01:43<05:12, 107kB/s]
+ 24%|##3 | 9.77M/41.5M [01:43<05:25, 102kB/s]
+ 24%|##3 | 9.79M/41.5M [01:43<05:34, 99.3kB/s]
+ 24%|##3 | 9.81M/41.5M [01:43<04:59, 111kB/s]
+ 24%|##3 | 9.83M/41.5M [01:44<05:36, 98.6kB/s]
+ 24%|##3 | 9.84M/41.5M [01:44<05:42, 96.8kB/s]
+ 24%|##3 | 9.86M/41.5M [01:44<05:24, 102kB/s]
+ 24%|##3 | 9.88M/41.5M [01:44<05:34, 99.2kB/s]
+ 24%|##3 | 9.89M/41.5M [01:44<05:41, 97.1kB/s]
+ 24%|##3 | 9.91M/41.5M [01:44<05:46, 95.6kB/s]
+ 24%|##3 | 9.92M/41.5M [01:45<05:49, 94.6kB/s]
+ 24%|##3 | 9.94M/41.5M [01:45<07:39, 72.0kB/s]
+ 24%|##4 | 9.97M/41.5M [01:45<05:30, 100kB/s]
+ 24%|##4 | 9.98M/41.5M [01:45<05:37, 98.0kB/s]
+ 24%|##4 | 10.0M/41.5M [01:46<05:42, 96.4kB/s]
+ 24%|##4 | 10.0M/41.5M [01:46<05:46, 95.2kB/s]
+ 24%|##4 | 10.0M/41.5M [01:46<07:52, 69.9kB/s]
+ 24%|##4 | 10.1M/41.5M [01:46<05:24, 102kB/s]
+ 24%|##4 | 10.1M/41.5M [01:47<06:32, 83.9kB/s]
+ 24%|##4 | 10.1M/41.5M [01:47<06:23, 85.9kB/s]
+ 24%|##4 | 10.1M/41.5M [01:47<06:15, 87.5kB/s]
+ 24%|##4 | 10.1M/41.5M [01:47<05:25, 101kB/s]
+ 24%|##4 | 10.1M/41.5M [01:47<05:33, 98.6kB/s]
+ 24%|##4 | 10.2M/41.5M [01:47<05:39, 96.8kB/s]
+ 25%|##4 | 10.2M/41.5M [01:48<05:01, 109kB/s]
+ 25%|##4 | 10.2M/41.5M [01:48<05:15, 104kB/s]
+ 25%|##4 | 10.2M/41.5M [01:48<04:47, 114kB/s]
+ 25%|##4 | 10.2M/41.5M [01:48<05:04, 108kB/s]
+ 25%|##4 | 10.3M/41.5M [01:48<05:18, 103kB/s]
+ 25%|##4 | 10.3M/41.5M [01:49<04:48, 114kB/s]
+ 25%|##4 | 10.3M/41.5M [01:49<05:05, 107kB/s]
+ 25%|##4 | 10.3M/41.5M [01:49<04:40, 116kB/s]
+ 25%|##4 | 10.3M/41.5M [01:49<04:25, 123kB/s]
+ 25%|##4 | 10.4M/41.5M [01:49<04:15, 128kB/s]
+ 25%|##5 | 10.4M/41.5M [01:49<04:09, 131kB/s]
+ 25%|##5 | 10.4M/41.5M [01:50<04:04, 133kB/s]
+ 25%|##5 | 10.4M/41.5M [01:50<04:01, 135kB/s]
+ 25%|##5 | 10.5M/41.5M [01:50<03:37, 150kB/s]
+ 25%|##5 | 10.5M/41.5M [01:50<03:42, 146kB/s]
+ 25%|##5 | 10.5M/41.5M [01:50<03:45, 144kB/s]
+ 25%|##5 | 10.5M/41.5M [01:50<03:28, 156kB/s]
+ 25%|##5 | 10.6M/41.5M [01:51<03:35, 151kB/s]
+ 26%|##5 | 10.6M/41.5M [01:51<03:21, 161kB/s]
+ 26%|##5 | 10.6M/41.5M [01:51<03:15, 166kB/s]
+ 26%|##5 | 10.7M/41.5M [01:51<03:08, 172kB/s]
+ 26%|##5 | 10.7M/41.5M [01:51<03:03, 176kB/s]
+ 26%|##5 | 10.7M/41.5M [01:52<03:00, 178kB/s]
+ 26%|##5 | 10.8M/41.5M [01:52<02:45, 194kB/s]
+ 26%|##6 | 10.8M/41.5M [01:52<02:35, 207kB/s]
+ 26%|##6 | 10.8M/41.5M [01:52<02:41, 200kB/s]
+ 26%|##6 | 10.8M/41.5M [01:52<03:27, 155kB/s]
+ 26%|##6 | 10.9M/41.5M [01:52<03:14, 165kB/s]
+ 26%|##6 | 10.9M/41.5M [01:53<02:34, 207kB/s]
+ 26%|##6 | 11.0M/41.5M [01:53<02:50, 188kB/s]
+ 26%|##6 | 11.0M/41.5M [01:53<03:03, 174kB/s]
+ 27%|##6 | 11.0M/41.5M [01:53<03:15, 164kB/s]
+ 27%|##6 | 11.0M/41.5M [01:53<03:07, 170kB/s]
+ 27%|##6 | 11.1M/41.5M [01:54<03:18, 161kB/s]
+ 27%|##6 | 11.1M/41.5M [01:54<03:10, 168kB/s]
+ 27%|##6 | 11.1M/41.5M [01:54<03:20, 159kB/s]
+ 27%|##6 | 11.1M/41.5M [01:54<03:13, 165kB/s]
+ 27%|##6 | 11.2M/41.5M [01:54<03:04, 172kB/s]
+ 27%|##6 | 11.2M/41.5M [01:54<03:02, 175kB/s]
+ 27%|##7 | 11.2M/41.5M [01:55<04:22, 121kB/s]
+ 27%|##7 | 11.3M/41.5M [01:55<03:03, 173kB/s]
+ 27%|##7 | 11.3M/41.5M [01:55<04:10, 127kB/s]
+ 27%|##7 | 11.3M/41.5M [01:55<03:45, 141kB/s]
+ 27%|##7 | 11.3M/41.5M [01:56<04:13, 125kB/s]
+ 27%|##7 | 11.4M/41.5M [01:56<04:31, 117kB/s]
+ 27%|##7 | 11.4M/41.5M [01:56<04:27, 118kB/s]
+ 27%|##7 | 11.4M/41.5M [01:56<04:26, 118kB/s]
+ 27%|##7 | 11.4M/41.5M [01:56<04:45, 111kB/s]
+ 28%|##7 | 11.4M/41.5M [01:56<05:00, 105kB/s]
+ 28%|##7 | 11.4M/41.5M [01:57<04:33, 115kB/s]
+ 28%|##7 | 11.5M/41.5M [01:57<04:51, 108kB/s]
+ 28%|##7 | 11.5M/41.5M [01:57<04:28, 117kB/s]
+ 28%|##7 | 11.5M/41.5M [01:57<04:31, 116kB/s]
+ 28%|##7 | 11.5M/41.5M [01:57<04:17, 122kB/s]
+ 28%|##7 | 11.5M/41.5M [01:58<04:07, 127kB/s]
+ 28%|##7 | 11.6M/41.5M [01:58<04:10, 125kB/s]
+ 28%|##7 | 11.6M/41.5M [01:58<03:53, 134kB/s]
+ 28%|##8 | 11.6M/41.5M [01:58<03:51, 135kB/s]
+ 28%|##8 | 11.6M/41.5M [01:58<03:49, 136kB/s]
+ 28%|##8 | 11.7M/41.5M [01:58<03:33, 147kB/s]
+ 28%|##8 | 11.7M/41.5M [01:59<03:36, 144kB/s]
+ 28%|##8 | 11.7M/41.5M [01:59<03:19, 157kB/s]
+ 28%|##8 | 11.7M/41.5M [01:59<04:44, 110kB/s]
+ 28%|##8 | 11.8M/41.5M [01:59<03:13, 161kB/s]
+ 28%|##8 | 11.8M/41.5M [01:59<03:20, 155kB/s]
+ 29%|##8 | 11.8M/41.5M [02:00<03:26, 151kB/s]
+ 29%|##8 | 11.9M/41.5M [02:00<03:17, 157kB/s]
+ 29%|##8 | 11.9M/41.5M [02:00<03:24, 151kB/s]
+ 29%|##8 | 11.9M/41.5M [02:00<03:24, 151kB/s]
+ 29%|##8 | 12.0M/41.5M [02:00<03:12, 161kB/s]
+ 29%|##8 | 12.0M/41.5M [02:01<03:04, 168kB/s]
+ 29%|##8 | 12.0M/41.5M [02:01<03:01, 170kB/s]
+ 29%|##8 | 12.0M/41.5M [02:01<02:56, 175kB/s]
+ 29%|##9 | 12.1M/41.5M [02:01<02:53, 178kB/s]
+ 29%|##9 | 12.1M/41.5M [02:01<02:51, 180kB/s]
+ 29%|##9 | 12.1M/41.5M [02:01<03:06, 166kB/s]
+ 29%|##9 | 12.1M/41.5M [02:01<03:16, 157kB/s]
+ 29%|##9 | 12.2M/41.5M [02:02<03:05, 166kB/s]
+ 29%|##9 | 12.2M/41.5M [02:02<02:59, 171kB/s]
+ 29%|##9 | 12.2M/41.5M [02:02<02:54, 176kB/s]
+ 30%|##9 | 12.2M/41.5M [02:02<03:06, 164kB/s]
+ 30%|##9 | 12.3M/41.5M [02:02<02:46, 184kB/s]
+ 30%|##9 | 12.3M/41.5M [02:02<02:45, 184kB/s]
+ 30%|##9 | 12.3M/41.5M [02:03<03:13, 158kB/s]
+ 30%|##9 | 12.4M/41.5M [02:03<02:50, 179kB/s]
+ 30%|##9 | 12.4M/41.5M [02:03<03:03, 166kB/s]
+ 30%|##9 | 12.4M/41.5M [02:03<02:57, 172kB/s]
+ 30%|##9 | 12.4M/41.5M [02:04<04:05, 124kB/s]
+ 30%|### | 12.5M/41.5M [02:04<02:55, 174kB/s]
+ 30%|### | 12.5M/41.5M [02:04<03:04, 164kB/s]
+ 30%|### | 12.5M/41.5M [02:04<04:05, 124kB/s]
+ 30%|### | 12.6M/41.5M [02:04<03:23, 149kB/s]
+ 30%|### | 12.6M/41.5M [02:05<03:27, 146kB/s]
+ 30%|### | 12.6M/41.5M [02:05<03:49, 132kB/s]
+ 30%|### | 12.6M/41.5M [02:05<05:18, 94.9kB/s]
+ 31%|### | 12.7M/41.5M [02:05<03:58, 127kB/s]
+ 31%|### | 12.7M/41.5M [02:06<04:08, 122kB/s]
+ 31%|### | 12.7M/41.5M [02:06<04:21, 115kB/s]
+ 31%|### | 12.7M/41.5M [02:06<04:19, 116kB/s]
+ 31%|### | 12.8M/41.5M [02:06<04:24, 114kB/s]
+ 31%|### | 12.8M/41.5M [02:06<04:36, 109kB/s]
+ 31%|### | 12.8M/41.5M [02:06<04:31, 111kB/s]
+ 31%|### | 12.8M/41.5M [02:07<04:28, 112kB/s]
+ 31%|### | 12.8M/41.5M [02:07<06:04, 82.4kB/s]
+ 31%|###1 | 12.9M/41.5M [02:07<04:15, 117kB/s]
+ 31%|###1 | 12.9M/41.5M [02:07<04:30, 111kB/s]
+ 31%|###1 | 12.9M/41.5M [02:07<04:43, 106kB/s]
+ 31%|###1 | 12.9M/41.5M [02:08<04:20, 115kB/s]
+ 31%|###1 | 12.9M/41.5M [02:08<04:35, 108kB/s]
+ 31%|###1 | 13.0M/41.5M [02:08<04:15, 117kB/s]
+ 31%|###1 | 13.0M/41.5M [02:08<04:02, 123kB/s]
+ 31%|###1 | 13.0M/41.5M [02:08<03:53, 128kB/s]
+ 31%|###1 | 13.0M/41.5M [02:09<04:14, 117kB/s]
+ 31%|###1 | 13.0M/41.5M [02:09<05:13, 95.0kB/s]
+ 32%|###1 | 13.1M/41.5M [02:09<03:51, 128kB/s]
+ 32%|###1 | 13.1M/41.5M [02:09<04:09, 119kB/s]
+ 32%|###1 | 13.1M/41.5M [02:09<04:26, 112kB/s]
+ 32%|###1 | 13.1M/41.5M [02:10<04:39, 106kB/s]
+ 32%|###1 | 13.1M/41.5M [02:10<04:50, 102kB/s]
+ 32%|###1 | 13.2M/41.5M [02:10<04:23, 113kB/s]
+ 32%|###1 | 13.2M/41.5M [02:10<04:06, 120kB/s]
+ 32%|###1 | 13.2M/41.5M [02:10<03:56, 126kB/s]
+ 32%|###1 | 13.2M/41.5M [02:11<03:49, 129kB/s]
+ 32%|###1 | 13.3M/41.5M [02:11<05:24, 91.1kB/s]
+ 32%|###2 | 13.3M/41.5M [02:11<03:55, 126kB/s]
+ 32%|###2 | 13.3M/41.5M [02:11<04:12, 117kB/s]
+ 32%|###2 | 13.3M/41.5M [02:11<04:27, 110kB/s]
+ 32%|###2 | 13.3M/41.5M [02:12<05:59, 82.1kB/s]
+ 32%|###2 | 13.4M/41.5M [02:12<04:11, 117kB/s]
+ 32%|###2 | 13.4M/41.5M [02:12<04:25, 111kB/s]
+ 32%|###2 | 13.4M/41.5M [02:12<04:37, 106kB/s]
+ 32%|###2 | 13.4M/41.5M [02:13<06:26, 76.1kB/s]
+ 32%|###2 | 13.5M/41.5M [02:13<05:08, 95.4kB/s]
+ 32%|###2 | 13.5M/41.5M [02:13<05:29, 89.2kB/s]
+ 33%|###2 | 13.5M/41.5M [02:13<05:26, 90.0kB/s]
+ 33%|###2 | 13.5M/41.5M [02:14<07:57, 61.5kB/s]
+ 33%|###2 | 13.5M/41.5M [02:14<05:37, 86.8kB/s]
+ 33%|###2 | 13.5M/41.5M [02:14<05:32, 88.1kB/s]
+ 33%|###2 | 13.6M/41.5M [02:14<06:49, 71.5kB/s]
+ 33%|###2 | 13.6M/41.5M [02:15<06:54, 70.6kB/s]
+ 33%|###2 | 13.6M/41.5M [02:15<06:27, 75.5kB/s]
+ 33%|###2 | 13.6M/41.5M [02:15<07:05, 68.7kB/s]
+ 33%|###2 | 13.6M/41.5M [02:16<10:04, 48.3kB/s]
+ 33%|###2 | 13.6M/41.5M [02:16<07:30, 64.8kB/s]
+ 33%|###2 | 13.6M/41.5M [02:16<08:00, 60.7kB/s]
+ 33%|###2 | 13.7M/41.5M [02:16<07:07, 68.2kB/s]
+ 33%|###2 | 13.7M/41.5M [02:16<07:45, 62.6kB/s]
+ 33%|###2 | 13.7M/41.5M [02:16<06:53, 70.5kB/s]
+ 33%|###3 | 13.7M/41.5M [02:17<07:36, 63.8kB/s]
+ 33%|###3 | 13.7M/41.5M [02:17<08:15, 58.8kB/s]
+ 33%|###3 | 13.7M/41.5M [02:17<11:10, 43.4kB/s]
+ 33%|###3 | 13.8M/41.5M [02:18<06:41, 72.4kB/s]
+ 33%|###3 | 13.8M/41.5M [02:18<07:22, 65.7kB/s]
+ 33%|###3 | 13.8M/41.5M [02:18<06:46, 71.5kB/s]
+ 33%|###3 | 13.8M/41.5M [02:18<06:41, 72.3kB/s]
+ 33%|###3 | 13.8M/41.5M [02:18<06:16, 77.1kB/s]
+ 33%|###3 | 13.8M/41.5M [02:19<05:58, 80.9kB/s]
+ 33%|###3 | 13.8M/41.5M [02:19<05:45, 84.0kB/s]
+ 33%|###3 | 13.9M/41.5M [02:19<05:35, 86.3kB/s]
+ 33%|###3 | 13.9M/41.5M [02:19<05:29, 88.0kB/s]
+ 33%|###3 | 13.9M/41.5M [02:19<05:24, 89.2kB/s]
+ 34%|###3 | 13.9M/41.5M [02:20<06:54, 69.7kB/s]
+ 34%|###3 | 13.9M/41.5M [02:20<05:34, 86.5kB/s]
+ 34%|###3 | 13.9M/41.5M [02:20<05:48, 82.9kB/s]
+ 34%|###3 | 14.0M/41.5M [02:20<05:17, 90.9kB/s]
+ 34%|###3 | 14.0M/41.5M [02:20<05:15, 91.3kB/s]
+ 34%|###3 | 14.0M/41.5M [02:21<05:14, 91.6kB/s]
+ 34%|###3 | 14.0M/41.5M [02:21<05:13, 91.8kB/s]
+ 34%|###3 | 14.0M/41.5M [02:21<05:13, 91.9kB/s]
+ 34%|###3 | 14.0M/41.5M [02:21<06:45, 70.9kB/s]
+ 34%|###3 | 14.1M/41.5M [02:21<04:50, 98.9kB/s]
+ 34%|###3 | 14.1M/41.5M [02:22<05:14, 91.5kB/s]
+ 34%|###3 | 14.1M/41.5M [02:22<05:13, 91.6kB/s]
+ 34%|###4 | 14.1M/41.5M [02:22<04:52, 98.2kB/s]
+ 34%|###4 | 14.1M/41.5M [02:22<04:57, 96.4kB/s]
+ 34%|###4 | 14.1M/41.5M [02:22<05:01, 95.2kB/s]
+ 34%|###4 | 14.2M/41.5M [02:23<05:03, 94.4kB/s]
+ 34%|###4 | 14.2M/41.5M [02:23<05:05, 93.7kB/s]
+ 34%|###4 | 14.2M/41.5M [02:23<06:38, 71.8kB/s]
+ 34%|###4 | 14.2M/41.5M [02:23<05:24, 88.2kB/s]
+ 34%|###4 | 14.2M/41.5M [02:23<05:20, 89.3kB/s]
+ 34%|###4 | 14.2M/41.5M [02:24<05:17, 90.1kB/s]
+ 34%|###4 | 14.3M/41.5M [02:24<05:14, 90.7kB/s]
+ 34%|###4 | 14.3M/41.5M [02:24<05:13, 91.1kB/s]
+ 34%|###4 | 14.3M/41.5M [02:24<05:11, 91.5kB/s]
+ 34%|###4 | 14.3M/41.5M [02:24<05:10, 91.7kB/s]
+ 35%|###4 | 14.3M/41.5M [02:24<05:10, 91.9kB/s]
+ 35%|###4 | 14.3M/41.5M [02:25<05:09, 92.0kB/s]
+ 35%|###4 | 14.4M/41.5M [02:25<04:28, 106kB/s]
+ 35%|###4 | 14.4M/41.5M [02:25<04:39, 102kB/s]
+ 35%|###4 | 14.4M/41.5M [02:25<04:47, 98.9kB/s]
+ 35%|###4 | 14.4M/41.5M [02:25<04:16, 111kB/s]
+ 35%|###4 | 14.4M/41.5M [02:26<06:10, 76.6kB/s]
+ 35%|###4 | 14.5M/41.5M [02:26<05:32, 85.2kB/s]
+ 35%|###4 | 14.5M/41.5M [02:26<03:48, 124kB/s]
+ 35%|###4 | 14.5M/41.5M [02:26<04:05, 115kB/s]
+ 35%|###5 | 14.5M/41.5M [02:26<04:20, 109kB/s]
+ 35%|###5 | 14.5M/41.5M [02:27<04:01, 117kB/s]
+ 35%|###5 | 14.6M/41.5M [02:27<04:16, 110kB/s]
+ 35%|###5 | 14.6M/41.5M [02:27<03:58, 118kB/s]
+ 35%|###5 | 14.6M/41.5M [02:27<05:30, 85.3kB/s]
+ 35%|###5 | 14.6M/41.5M [02:27<03:52, 121kB/s]
+ 35%|###5 | 14.7M/41.5M [02:28<04:07, 113kB/s]
+ 35%|###5 | 14.7M/41.5M [02:28<04:21, 108kB/s]
+ 35%|###5 | 14.7M/41.5M [02:28<04:01, 116kB/s]
+ 35%|###5 | 14.7M/41.5M [02:28<04:16, 109kB/s]
+ 36%|###5 | 14.7M/41.5M [02:28<03:58, 118kB/s]
+ 36%|###5 | 14.8M/41.5M [02:29<03:46, 124kB/s]
+ 36%|###5 | 14.8M/41.5M [02:29<04:04, 115kB/s]
+ 36%|###5 | 14.8M/41.5M [02:29<03:50, 122kB/s]
+ 36%|###5 | 14.8M/41.5M [02:29<04:43, 98.6kB/s]
+ 36%|###5 | 14.8M/41.5M [02:29<03:34, 130kB/s]
+ 36%|###5 | 14.9M/41.5M [02:29<03:54, 119kB/s]
+ 36%|###5 | 14.9M/41.5M [02:30<04:10, 111kB/s]
+ 36%|###5 | 14.9M/41.5M [02:30<04:23, 106kB/s]
+ 36%|###5 | 14.9M/41.5M [02:30<04:14, 110kB/s]
+ 36%|###5 | 14.9M/41.5M [02:30<05:29, 84.7kB/s]
+ 36%|###6 | 15.0M/41.5M [02:31<04:16, 109kB/s]
+ 36%|###6 | 15.0M/41.5M [02:31<04:25, 105kB/s]
+ 36%|###6 | 15.0M/41.5M [02:31<04:33, 102kB/s]
+ 36%|###6 | 15.0M/41.5M [02:31<04:09, 111kB/s]
+ 36%|###6 | 15.0M/41.5M [02:31<04:20, 106kB/s]
+ 36%|###6 | 15.1M/41.5M [02:31<03:59, 116kB/s]
+ 36%|###6 | 15.1M/41.5M [02:32<03:46, 122kB/s]
+ 36%|###6 | 15.1M/41.5M [02:32<04:04, 113kB/s]
+ 36%|###6 | 15.1M/41.5M [02:32<03:48, 121kB/s]
+ 36%|###6 | 15.1M/41.5M [02:32<03:39, 126kB/s]
+ 37%|###6 | 15.2M/41.5M [02:32<03:32, 130kB/s]
+ 37%|###6 | 15.2M/41.5M [02:33<03:28, 132kB/s]
+ 37%|###6 | 15.2M/41.5M [02:33<03:49, 120kB/s]
+ 37%|###6 | 15.2M/41.5M [02:33<03:17, 139kB/s]
+ 37%|###6 | 15.3M/41.5M [02:33<03:18, 139kB/s]
+ 37%|###6 | 15.3M/41.5M [02:33<03:17, 139kB/s]
+ 37%|###6 | 15.3M/41.5M [02:33<03:17, 139kB/s]
+ 37%|###6 | 15.3M/41.5M [02:34<03:17, 139kB/s]
+ 37%|###6 | 15.3M/41.5M [02:34<03:40, 124kB/s]
+ 37%|###7 | 15.4M/41.5M [02:34<03:11, 143kB/s]
+ 37%|###7 | 15.4M/41.5M [02:34<03:13, 141kB/s]
+ 37%|###7 | 15.4M/41.5M [02:34<03:35, 127kB/s]
+ 37%|###7 | 15.4M/41.5M [02:34<03:09, 144kB/s]
+ 37%|###7 | 15.5M/41.5M [02:35<03:11, 142kB/s]
+ 37%|###7 | 15.5M/41.5M [02:35<03:13, 141kB/s]
+ 37%|###7 | 15.5M/41.5M [02:35<03:14, 140kB/s]
+ 37%|###7 | 15.5M/41.5M [02:35<02:57, 153kB/s]
+ 38%|###7 | 15.6M/41.5M [02:35<03:22, 135kB/s]
+ 38%|###7 | 15.6M/41.5M [02:36<03:01, 150kB/s]
+ 38%|###7 | 15.6M/41.5M [02:36<03:05, 146kB/s]
+ 38%|###7 | 15.6M/41.5M [02:36<03:28, 130kB/s]
+ 38%|###7 | 15.6M/41.5M [02:36<03:48, 118kB/s]
+ 38%|###7 | 15.7M/41.5M [02:36<03:37, 125kB/s]
+ 38%|###7 | 15.7M/41.5M [02:37<05:06, 88.1kB/s]
+ 38%|###7 | 15.7M/41.5M [02:37<04:28, 101kB/s]
+ 38%|###7 | 15.7M/41.5M [02:37<04:34, 98.5kB/s]
+ 38%|###7 | 15.7M/41.5M [02:37<04:38, 96.8kB/s]
+ 38%|###7 | 15.8M/41.5M [02:37<04:42, 95.5kB/s]
+ 38%|###8 | 15.8M/41.5M [02:38<07:28, 60.2kB/s]
+ 38%|###8 | 15.8M/41.5M [02:38<05:14, 85.8kB/s]
+ 38%|###8 | 15.8M/41.5M [02:38<05:08, 87.2kB/s]
+ 38%|###8 | 15.8M/41.5M [02:38<05:04, 88.5kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<05:00, 89.5kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<04:57, 90.2kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<04:55, 90.8kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<04:54, 91.2kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<04:52, 91.5kB/s]
+ 38%|###8 | 15.9M/41.5M [02:39<04:52, 91.7kB/s]
+ 38%|###8 | 15.9M/41.5M [02:40<04:51, 91.9kB/s]
+ 38%|###8 | 16.0M/41.5M [02:40<04:50, 92.0kB/s]
+ 39%|###8 | 16.0M/41.5M [02:40<04:50, 92.1kB/s]
+ 39%|###8 | 16.0M/41.5M [02:40<04:50, 92.1kB/s]
+ 39%|###8 | 16.0M/41.5M [02:40<04:12, 106kB/s]
+ 39%|###8 | 16.0M/41.5M [02:40<04:22, 102kB/s]
+ 39%|###8 | 16.1M/41.5M [02:41<03:56, 113kB/s]
+ 39%|###8 | 16.1M/41.5M [02:41<03:41, 120kB/s]
+ 39%|###8 | 16.1M/41.5M [02:41<03:57, 112kB/s]
+ 39%|###8 | 16.1M/41.5M [02:41<04:29, 98.9kB/s]
+ 39%|###8 | 16.1M/41.5M [02:41<03:20, 132kB/s]
+ 39%|###8 | 16.2M/41.5M [02:42<03:41, 120kB/s]
+ 39%|###8 | 16.2M/41.5M [02:42<05:10, 85.6kB/s]
+ 39%|###9 | 16.2M/41.5M [02:42<06:20, 69.8kB/s]
+ 39%|###9 | 16.2M/41.5M [02:42<04:38, 95.2kB/s]
+ 39%|###9 | 16.2M/41.5M [02:43<04:40, 94.5kB/s]
+ 39%|###9 | 16.2M/41.5M [02:43<04:41, 93.9kB/s]
+ 39%|###9 | 16.3M/41.5M [02:43<04:43, 93.5kB/s]
+ 39%|###9 | 16.3M/41.5M [02:43<06:39, 66.2kB/s]
+ 39%|###9 | 16.3M/41.5M [02:44<05:20, 82.5kB/s]
+ 39%|###9 | 16.3M/41.5M [02:44<05:11, 84.6kB/s]
+ 39%|###9 | 16.3M/41.5M [02:44<05:05, 86.4kB/s]
+ 39%|###9 | 16.4M/41.5M [02:45<07:31, 58.3kB/s]
+ 40%|###9 | 16.4M/41.5M [02:45<07:21, 59.6kB/s]
+ 40%|###9 | 16.4M/41.5M [02:45<05:27, 80.4kB/s]
+ 40%|###9 | 16.4M/41.5M [02:45<05:17, 82.7kB/s]
+ 40%|###9 | 16.5M/41.5M [02:46<06:16, 69.7kB/s]
+ 40%|###9 | 16.5M/41.5M [02:46<05:53, 74.3kB/s]
+ 40%|###9 | 16.5M/41.5M [02:46<05:34, 78.3kB/s]
+ 40%|###9 | 16.5M/41.5M [02:46<05:20, 81.7kB/s]
+ 40%|###9 | 16.5M/41.5M [02:47<05:10, 84.2kB/s]
+ 40%|###9 | 16.5M/41.5M [02:47<07:45, 56.2kB/s]
+ 40%|###9 | 16.6M/41.5M [02:47<05:19, 81.7kB/s]
+ 40%|###9 | 16.6M/41.5M [02:47<05:10, 84.0kB/s]
+ 40%|###9 | 16.6M/41.5M [02:48<05:03, 86.0kB/s]
+ 40%|#### | 16.6M/41.5M [02:48<04:57, 87.6kB/s]
+ 40%|#### | 16.6M/41.5M [02:48<07:30, 57.9kB/s]
+ 40%|#### | 16.7M/41.5M [02:48<05:13, 83.1kB/s]
+ 40%|#### | 16.7M/41.5M [02:49<05:05, 85.2kB/s]
+ 40%|#### | 16.7M/41.5M [02:49<04:59, 86.9kB/s]
+ 40%|#### | 16.7M/41.5M [02:49<04:54, 88.2kB/s]
+ 40%|#### | 16.7M/41.5M [02:49<04:50, 89.3kB/s]
+ 40%|#### | 16.7M/41.5M [02:49<04:48, 90.0kB/s]
+ 40%|#### | 16.8M/41.5M [02:50<04:46, 90.6kB/s]
+ 40%|#### | 16.8M/41.5M [02:50<04:44, 91.1kB/s]
+ 40%|#### | 16.8M/41.5M [02:50<04:43, 91.4kB/s]
+ 40%|#### | 16.8M/41.5M [02:50<04:42, 91.7kB/s]
+ 41%|#### | 16.8M/41.5M [02:50<04:41, 91.8kB/s]
+ 41%|#### | 16.8M/41.5M [02:50<04:41, 92.0kB/s]
+ 41%|#### | 16.8M/41.5M [02:51<04:40, 92.1kB/s]
+ 41%|#### | 16.9M/41.5M [02:51<04:03, 106kB/s]
+ 41%|#### | 16.9M/41.5M [02:51<05:29, 78.3kB/s]
+ 41%|#### | 16.9M/41.5M [02:51<04:06, 105kB/s]
+ 41%|#### | 16.9M/41.5M [02:52<04:14, 101kB/s]
+ 41%|#### | 16.9M/41.5M [02:52<04:20, 98.9kB/s]
+ 41%|#### | 17.0M/41.5M [02:52<03:53, 110kB/s]
+ 41%|#### | 17.0M/41.5M [02:52<04:05, 105kB/s]
+ 41%|#### | 17.0M/41.5M [02:52<03:44, 115kB/s]
+ 41%|####1 | 17.0M/41.5M [02:52<03:57, 108kB/s]
+ 41%|####1 | 17.0M/41.5M [02:53<03:39, 117kB/s]
+ 41%|####1 | 17.1M/41.5M [02:53<03:53, 110kB/s]
+ 41%|####1 | 17.1M/41.5M [02:53<03:36, 118kB/s]
+ 41%|####1 | 17.1M/41.5M [02:53<03:51, 110kB/s]
+ 41%|####1 | 17.1M/41.5M [02:53<04:39, 91.3kB/s]
+ 41%|####1 | 17.2M/41.5M [02:54<03:42, 114kB/s]
+ 41%|####1 | 17.2M/41.5M [02:54<03:54, 109kB/s]
+ 41%|####1 | 17.2M/41.5M [02:54<04:04, 104kB/s]
+ 41%|####1 | 17.2M/41.5M [02:54<03:43, 114kB/s]
+ 42%|####1 | 17.2M/41.5M [02:54<03:56, 108kB/s]
+ 42%|####1 | 17.2M/41.5M [02:55<03:38, 117kB/s]
+ 42%|####1 | 17.3M/41.5M [02:55<03:26, 123kB/s]
+ 42%|####1 | 17.3M/41.5M [02:55<03:19, 127kB/s]
+ 42%|####1 | 17.3M/41.5M [02:55<03:36, 117kB/s]
+ 42%|####1 | 17.3M/41.5M [02:55<03:25, 123kB/s]
+ 42%|####1 | 17.4M/41.5M [02:55<03:17, 128kB/s]
+ 42%|####1 | 17.4M/41.5M [02:56<03:13, 131kB/s]
+ 42%|####1 | 17.4M/41.5M [02:56<03:09, 133kB/s]
+ 42%|####2 | 17.4M/41.5M [02:56<03:07, 135kB/s]
+ 42%|####2 | 17.5M/41.5M [02:56<03:05, 136kB/s]
+ 42%|####2 | 17.5M/41.5M [02:56<03:04, 137kB/s]
+ 42%|####2 | 17.5M/41.5M [02:56<03:03, 137kB/s]
+ 42%|####2 | 17.5M/41.5M [02:57<03:38, 115kB/s]
+ 42%|####2 | 17.5M/41.5M [02:57<03:26, 122kB/s]
+ 42%|####2 | 17.6M/41.5M [02:57<04:30, 92.7kB/s]
+ 42%|####2 | 17.6M/41.5M [02:57<04:47, 87.2kB/s]
+ 42%|####2 | 17.6M/41.5M [02:58<03:43, 112kB/s]
+ 42%|####2 | 17.6M/41.5M [02:58<03:54, 107kB/s]
+ 42%|####2 | 17.6M/41.5M [02:58<04:03, 103kB/s]
+ 43%|####2 | 17.6M/41.5M [02:58<04:10, 99.7kB/s]
+ 43%|####2 | 17.7M/41.5M [02:58<04:16, 97.5kB/s]
+ 43%|####2 | 17.7M/41.5M [02:58<04:20, 96.0kB/s]
+ 43%|####2 | 17.7M/41.5M [02:59<04:22, 94.9kB/s]
+ 43%|####2 | 17.7M/41.5M [02:59<04:24, 94.1kB/s]
+ 43%|####2 | 17.7M/41.5M [02:59<07:04, 58.7kB/s]
+ 43%|####2 | 17.8M/41.5M [03:00<04:34, 90.5kB/s]
+ 43%|####2 | 17.8M/41.5M [03:00<06:35, 62.8kB/s]
+ 43%|####2 | 17.8M/41.5M [03:00<04:27, 92.8kB/s]
+ 43%|####2 | 17.8M/41.5M [03:00<04:27, 92.7kB/s]
+ 43%|####3 | 17.9M/41.5M [03:01<04:27, 92.6kB/s]
+ 43%|####3 | 17.9M/41.5M [03:01<05:33, 74.4kB/s]
+ 43%|####3 | 17.9M/41.5M [03:01<05:16, 78.3kB/s]
+ 43%|####3 | 17.9M/41.5M [03:01<05:03, 81.6kB/s]
+ 43%|####3 | 17.9M/41.5M [03:02<04:53, 84.2kB/s]
+ 43%|####3 | 17.9M/41.5M [03:02<04:46, 86.3kB/s]
+ 43%|####3 | 17.9M/41.5M [03:02<04:40, 88.0kB/s]
+ 43%|####3 | 18.0M/41.5M [03:02<04:36, 89.2kB/s]
+ 43%|####3 | 18.0M/41.5M [03:02<03:58, 103kB/s]
+ 43%|####3 | 18.0M/41.5M [03:02<04:05, 100kB/s]
+ 43%|####3 | 18.0M/41.5M [03:03<03:41, 111kB/s]
+ 43%|####3 | 18.0M/41.5M [03:03<03:52, 106kB/s]
+ 44%|####3 | 18.1M/41.5M [03:03<03:32, 115kB/s]
+ 44%|####3 | 18.1M/41.5M [03:03<03:20, 122kB/s]
+ 44%|####3 | 18.1M/41.5M [03:03<03:36, 113kB/s]
+ 44%|####3 | 18.1M/41.5M [03:04<04:57, 82.3kB/s]
+ 44%|####3 | 18.2M/41.5M [03:04<03:18, 123kB/s]
+ 44%|####3 | 18.2M/41.5M [03:04<03:31, 116kB/s]
+ 44%|####3 | 18.2M/41.5M [03:04<03:20, 122kB/s]
+ 44%|####3 | 18.2M/41.5M [03:04<03:13, 126kB/s]
+ 44%|####3 | 18.2M/41.5M [03:05<03:08, 130kB/s]
+ 44%|####4 | 18.3M/41.5M [03:05<03:04, 132kB/s]
+ 44%|####4 | 18.3M/41.5M [03:05<03:01, 134kB/s]
+ 44%|####4 | 18.3M/41.5M [03:05<02:59, 135kB/s]
+ 44%|####4 | 18.3M/41.5M [03:06<04:16, 94.5kB/s]
+ 44%|####4 | 18.4M/41.5M [03:06<02:54, 139kB/s]
+ 44%|####4 | 18.4M/41.5M [03:06<03:10, 127kB/s]
+ 44%|####4 | 18.4M/41.5M [03:06<03:25, 118kB/s]
+ 44%|####4 | 18.4M/41.5M [03:06<03:15, 123kB/s]
+ 44%|####4 | 18.5M/41.5M [03:06<03:31, 114kB/s]
+ 45%|####4 | 18.5M/41.5M [03:07<02:59, 135kB/s]
+ 45%|####4 | 18.5M/41.5M [03:07<03:17, 122kB/s]
+ 45%|####4 | 18.5M/41.5M [03:07<03:32, 113kB/s]
+ 45%|####4 | 18.5M/41.5M [03:07<03:44, 107kB/s]
+ 45%|####4 | 18.6M/41.5M [03:07<03:26, 116kB/s]
+ 45%|####4 | 18.6M/41.5M [03:07<03:40, 109kB/s]
+ 45%|####4 | 18.6M/41.5M [03:08<03:50, 104kB/s]
+ 45%|####4 | 18.6M/41.5M [03:08<03:29, 114kB/s]
+ 45%|####4 | 18.6M/41.5M [03:08<03:42, 108kB/s]
+ 45%|####4 | 18.6M/41.5M [03:08<03:24, 117kB/s]
+ 45%|####5 | 18.7M/41.5M [03:08<03:14, 123kB/s]
+ 45%|####5 | 18.7M/41.5M [03:09<03:06, 128kB/s]
+ 45%|####5 | 18.7M/41.5M [03:09<03:02, 131kB/s]
+ 45%|####5 | 18.7M/41.5M [03:09<02:59, 133kB/s]
+ 45%|####5 | 18.8M/41.5M [03:09<02:56, 135kB/s]
+ 45%|####5 | 18.8M/41.5M [03:09<03:29, 114kB/s]
+ 45%|####5 | 18.8M/41.5M [03:09<03:03, 130kB/s]
+ 45%|####5 | 18.8M/41.5M [03:10<03:20, 118kB/s]
+ 45%|####5 | 18.8M/41.5M [03:10<03:10, 124kB/s]
+ 45%|####5 | 18.9M/41.5M [03:10<03:04, 129kB/s]
+ 46%|####5 | 18.9M/41.5M [03:10<03:00, 132kB/s]
+ 46%|####5 | 18.9M/41.5M [03:10<02:57, 134kB/s]
+ 46%|####5 | 18.9M/41.5M [03:10<02:55, 135kB/s]
+ 46%|####5 | 19.0M/41.5M [03:11<02:53, 136kB/s]
+ 46%|####5 | 19.0M/41.5M [03:11<02:52, 137kB/s]
+ 46%|####5 | 19.0M/41.5M [03:11<02:36, 151kB/s]
+ 46%|####5 | 19.0M/41.5M [03:11<02:39, 147kB/s]
+ 46%|####5 | 19.1M/41.5M [03:11<02:42, 145kB/s]
+ 46%|####6 | 19.1M/41.5M [03:12<02:44, 143kB/s]
+ 46%|####6 | 19.1M/41.5M [03:12<02:31, 155kB/s]
+ 46%|####6 | 19.1M/41.5M [03:12<02:35, 150kB/s]
+ 46%|####6 | 19.2M/41.5M [03:12<02:25, 160kB/s]
+ 46%|####6 | 19.2M/41.5M [03:12<02:31, 154kB/s]
+ 46%|####6 | 19.2M/41.5M [03:12<02:23, 163kB/s]
+ 46%|####6 | 19.2M/41.5M [03:13<02:29, 156kB/s]
+ 46%|####6 | 19.3M/41.5M [03:13<03:02, 127kB/s]
+ 47%|####6 | 19.3M/41.5M [03:13<02:18, 168kB/s]
+ 47%|####6 | 19.3M/41.5M [03:13<02:26, 159kB/s]
+ 47%|####6 | 19.4M/41.5M [03:13<02:31, 153kB/s]
+ 47%|####6 | 19.4M/41.5M [03:14<02:22, 162kB/s]
+ 47%|####6 | 19.4M/41.5M [03:14<02:29, 155kB/s]
+ 47%|####6 | 19.4M/41.5M [03:14<02:20, 164kB/s]
+ 47%|####6 | 19.5M/41.5M [03:14<02:15, 170kB/s]
+ 47%|####6 | 19.5M/41.5M [03:14<02:12, 174kB/s]
+ 47%|####7 | 19.5M/41.5M [03:14<02:40, 143kB/s]
+ 47%|####7 | 19.6M/41.5M [03:15<02:07, 180kB/s]
+ 47%|####7 | 19.6M/41.5M [03:15<02:16, 168kB/s]
+ 47%|####7 | 19.6M/41.5M [03:15<02:23, 160kB/s]
+ 47%|####7 | 19.6M/41.5M [03:15<02:19, 164kB/s]
+ 47%|####7 | 19.7M/41.5M [03:15<02:15, 169kB/s]
+ 47%|####7 | 19.7M/41.5M [03:15<02:23, 159kB/s]
+ 48%|####7 | 19.7M/41.5M [03:16<02:16, 167kB/s]
+ 48%|####7 | 19.7M/41.5M [03:16<02:11, 173kB/s]
+ 48%|####7 | 19.8M/41.5M [03:16<02:09, 176kB/s]
+ 48%|####7 | 19.8M/41.5M [03:16<02:08, 177kB/s]
+ 48%|####7 | 19.8M/41.5M [03:16<02:07, 179kB/s]
+ 48%|####7 | 19.8M/41.5M [03:16<02:17, 165kB/s]
+ 48%|####7 | 19.9M/41.5M [03:17<02:12, 171kB/s]
+ 48%|####7 | 19.9M/41.5M [03:17<02:08, 176kB/s]
+ 48%|####8 | 19.9M/41.5M [03:17<02:06, 178kB/s]
+ 48%|####8 | 20.0M/41.5M [03:17<02:05, 180kB/s]
+ 48%|####8 | 20.0M/41.5M [03:17<02:03, 183kB/s]
+ 48%|####8 | 20.0M/41.5M [03:17<02:02, 184kB/s]
+ 48%|####8 | 20.0M/41.5M [03:17<02:02, 184kB/s]
+ 48%|####8 | 20.1M/41.5M [03:18<02:01, 184kB/s]
+ 48%|####8 | 20.1M/41.5M [03:18<02:34, 145kB/s]
+ 49%|####8 | 20.1M/41.5M [03:18<01:53, 197kB/s]
+ 49%|####8 | 20.2M/41.5M [03:18<01:55, 194kB/s]
+ 49%|####8 | 20.2M/41.5M [03:18<02:06, 176kB/s]
+ 49%|####8 | 20.2M/41.5M [03:19<02:04, 179kB/s]
+ 49%|####8 | 20.2M/41.5M [03:19<02:03, 181kB/s]
+ 49%|####8 | 20.3M/41.5M [03:19<02:02, 182kB/s]
+ 49%|####8 | 20.3M/41.5M [03:19<02:01, 183kB/s]
+ 49%|####9 | 20.4M/41.5M [03:19<02:00, 184kB/s]
+ 49%|####9 | 20.4M/41.5M [03:19<01:51, 198kB/s]
+ 49%|####9 | 20.4M/41.5M [03:20<01:54, 194kB/s]
+ 49%|####9 | 20.5M/41.5M [03:20<01:47, 205kB/s]
+ 49%|####9 | 20.5M/41.5M [03:20<01:50, 198kB/s]
+ 49%|####9 | 20.5M/41.5M [03:20<01:45, 209kB/s]
+ 50%|####9 | 20.6M/41.5M [03:20<01:41, 217kB/s]
+ 50%|####9 | 20.6M/41.5M [03:20<01:45, 208kB/s]
+ 50%|####9 | 20.6M/41.5M [03:21<01:47, 204kB/s]
+ 50%|####9 | 20.6M/41.5M [03:21<02:32, 144kB/s]
+ 50%|####9 | 20.7M/41.5M [03:21<01:52, 194kB/s]
+ 50%|####9 | 20.7M/41.5M [03:21<01:53, 191kB/s]
+ 50%|####9 | 20.7M/41.5M [03:21<01:54, 189kB/s]
+ 50%|##### | 20.8M/41.5M [03:22<02:42, 134kB/s]
+ 50%|##### | 20.8M/41.5M [03:22<02:00, 180kB/s]
+ 50%|##### | 20.8M/41.5M [03:22<02:08, 168kB/s]
+ 50%|##### | 20.9M/41.5M [03:22<02:15, 160kB/s]
+ 50%|##### | 20.9M/41.5M [03:22<02:20, 154kB/s]
+ 50%|##### | 20.9M/41.5M [03:23<02:24, 149kB/s]
+ 50%|##### | 20.9M/41.5M [03:23<02:27, 146kB/s]
+ 51%|##### | 21.0M/41.5M [03:23<02:19, 155kB/s]
+ 51%|##### | 21.0M/41.5M [03:23<02:25, 148kB/s]
+ 51%|##### | 21.0M/41.5M [03:23<02:16, 158kB/s]
+ 51%|##### | 21.0M/41.5M [03:23<02:10, 164kB/s]
+ 51%|##### | 21.0M/41.5M [03:24<02:54, 123kB/s]
+ 51%|##### | 21.1M/41.5M [03:24<02:21, 152kB/s]
+ 51%|##### | 21.1M/41.5M [03:24<02:24, 148kB/s]
+ 51%|##### | 21.1M/41.5M [03:24<02:43, 131kB/s]
+ 51%|##### | 21.1M/41.5M [03:24<02:40, 133kB/s]
+ 51%|##### | 21.2M/41.5M [03:24<02:25, 146kB/s]
+ 51%|#####1 | 21.2M/41.5M [03:25<02:17, 155kB/s]
+ 51%|#####1 | 21.2M/41.5M [03:25<03:16, 108kB/s]
+ 51%|#####1 | 21.2M/41.5M [03:25<02:19, 152kB/s]
+ 51%|#####1 | 21.3M/41.5M [03:25<02:23, 148kB/s]
+ 51%|#####1 | 21.3M/41.5M [03:25<02:26, 145kB/s]
+ 51%|#####1 | 21.3M/41.5M [03:26<02:43, 129kB/s]
+ 51%|#####1 | 21.3M/41.5M [03:26<02:44, 128kB/s]
+ 51%|#####1 | 21.3M/41.5M [03:26<02:40, 131kB/s]
+ 52%|#####1 | 21.4M/41.5M [03:26<02:22, 148kB/s]
+ 52%|#####1 | 21.4M/41.5M [03:26<02:25, 145kB/s]
+ 52%|#####1 | 21.4M/41.5M [03:26<02:13, 157kB/s]
+ 52%|#####1 | 21.4M/41.5M [03:27<02:45, 127kB/s]
+ 52%|#####1 | 21.5M/41.5M [03:27<02:15, 155kB/s]
+ 52%|#####1 | 21.5M/41.5M [03:27<02:19, 150kB/s]
+ 52%|#####1 | 21.5M/41.5M [03:27<03:39, 95.5kB/s]
+ 52%|#####1 | 21.6M/41.5M [03:27<02:21, 148kB/s]
+ 52%|#####2 | 21.6M/41.5M [03:28<03:12, 109kB/s]
+ 52%|#####2 | 21.6M/41.5M [03:28<02:36, 133kB/s]
+ 52%|#####2 | 21.6M/41.5M [03:28<02:44, 126kB/s]
+ 52%|#####2 | 21.6M/41.5M [03:28<02:56, 118kB/s]
+ 52%|#####2 | 21.7M/41.5M [03:29<03:07, 111kB/s]
+ 52%|#####2 | 21.7M/41.5M [03:29<03:02, 114kB/s]
+ 52%|#####2 | 21.7M/41.5M [03:29<02:51, 121kB/s]
+ 52%|#####2 | 21.7M/41.5M [03:29<03:04, 113kB/s]
+ 52%|#####2 | 21.7M/41.5M [03:29<02:52, 120kB/s]
+ 52%|#####2 | 21.8M/41.5M [03:29<03:19, 104kB/s]
+ 52%|#####2 | 21.8M/41.5M [03:30<02:48, 123kB/s]
+ 53%|#####2 | 21.8M/41.5M [03:30<03:02, 113kB/s]
+ 53%|#####2 | 21.8M/41.5M [03:30<03:12, 107kB/s]
+ 53%|#####2 | 21.8M/41.5M [03:30<03:21, 103kB/s]
+ 53%|#####2 | 21.9M/41.5M [03:30<03:01, 113kB/s]
+ 53%|#####2 | 21.9M/41.5M [03:30<02:50, 121kB/s]
+ 53%|#####2 | 21.9M/41.5M [03:31<03:03, 112kB/s]
+ 53%|#####2 | 21.9M/41.5M [03:31<02:50, 120kB/s]
+ 53%|#####2 | 21.9M/41.5M [03:31<02:43, 126kB/s]
+ 53%|#####2 | 22.0M/41.5M [03:31<02:38, 129kB/s]
+ 53%|#####2 | 22.0M/41.5M [03:31<02:52, 118kB/s]
+ 53%|#####3 | 22.0M/41.5M [03:32<02:44, 124kB/s]
+ 53%|#####3 | 22.0M/41.5M [03:32<02:38, 128kB/s]
+ 53%|#####3 | 22.0M/41.5M [03:32<03:45, 90.3kB/s]
+ 53%|#####3 | 22.1M/41.5M [03:32<02:29, 137kB/s]
+ 53%|#####3 | 22.1M/41.5M [03:32<02:42, 125kB/s]
+ 53%|#####3 | 22.1M/41.5M [03:33<03:18, 102kB/s]
+ 53%|#####3 | 22.1M/41.5M [03:33<02:51, 118kB/s]
+ 53%|#####3 | 22.2M/41.5M [03:33<03:02, 111kB/s]
+ 53%|#####3 | 22.2M/41.5M [03:33<03:11, 106kB/s]
+ 53%|#####3 | 22.2M/41.5M [03:33<03:18, 102kB/s]
+ 54%|#####3 | 22.2M/41.5M [03:34<03:24, 99.0kB/s]
+ 54%|#####3 | 22.2M/41.5M [03:34<03:27, 97.2kB/s]
+ 54%|#####3 | 22.2M/41.5M [03:34<03:30, 95.7kB/s]
+ 54%|#####3 | 22.2M/41.5M [03:34<03:32, 95.2kB/s]
+ 54%|#####3 | 22.3M/41.5M [03:34<03:18, 102kB/s]
+ 54%|#####3 | 22.3M/41.5M [03:34<03:06, 108kB/s]
+ 54%|#####3 | 22.3M/41.5M [03:35<04:38, 72.3kB/s]
+ 54%|#####3 | 22.3M/41.5M [03:35<03:06, 107kB/s]
+ 54%|#####3 | 22.3M/41.5M [03:35<03:14, 103kB/s]
+ 54%|#####3 | 22.4M/41.5M [03:35<03:20, 100kB/s]
+ 54%|#####3 | 22.4M/41.5M [03:35<03:24, 97.9kB/s]
+ 54%|#####3 | 22.4M/41.5M [03:36<03:02, 109kB/s]
+ 54%|#####4 | 22.4M/41.5M [03:36<03:11, 105kB/s]
+ 54%|#####4 | 22.4M/41.5M [03:36<02:54, 115kB/s]
+ 54%|#####4 | 22.5M/41.5M [03:36<04:00, 83.1kB/s]
+ 54%|#####4 | 22.5M/41.5M [03:36<03:04, 108kB/s]
+ 54%|#####4 | 22.5M/41.5M [03:37<03:11, 104kB/s]
+ 54%|#####4 | 22.5M/41.5M [03:37<03:17, 101kB/s]
+ 54%|#####4 | 22.5M/41.5M [03:37<03:21, 98.4kB/s]
+ 54%|#####4 | 22.6M/41.5M [03:37<03:00, 110kB/s]
+ 54%|#####4 | 22.6M/41.5M [03:37<03:09, 105kB/s]
+ 54%|#####4 | 22.6M/41.5M [03:38<02:52, 115kB/s]
+ 54%|#####4 | 22.6M/41.5M [03:38<03:03, 108kB/s]
+ 55%|#####4 | 22.6M/41.5M [03:38<03:11, 103kB/s]
+ 55%|#####4 | 22.6M/41.5M [03:38<02:53, 114kB/s]
+ 55%|#####4 | 22.7M/41.5M [03:38<03:03, 107kB/s]
+ 55%|#####4 | 22.7M/41.5M [03:38<02:49, 117kB/s]
+ 55%|#####4 | 22.7M/41.5M [03:39<02:39, 123kB/s]
+ 55%|#####4 | 22.7M/41.5M [03:39<02:33, 128kB/s]
+ 55%|#####4 | 22.8M/41.5M [03:39<02:47, 117kB/s]
+ 55%|#####4 | 22.8M/41.5M [03:39<02:22, 137kB/s]
+ 55%|#####4 | 22.8M/41.5M [03:40<03:36, 90.4kB/s]
+ 55%|#####5 | 22.8M/41.5M [03:40<03:01, 108kB/s]
+ 55%|#####5 | 22.9M/41.5M [03:40<02:36, 124kB/s]
+ 55%|#####5 | 22.9M/41.5M [03:40<02:46, 117kB/s]
+ 55%|#####5 | 22.9M/41.5M [03:40<02:56, 111kB/s]
+ 55%|#####5 | 22.9M/41.5M [03:41<03:15, 99.7kB/s]
+ 55%|#####5 | 22.9M/41.5M [03:41<03:19, 97.6kB/s]
+ 55%|#####5 | 23.0M/41.5M [03:41<03:21, 96.3kB/s]
+ 55%|#####5 | 23.0M/41.5M [03:41<03:24, 95.2kB/s]
+ 55%|#####5 | 23.0M/41.5M [03:41<03:25, 94.3kB/s]
+ 55%|#####5 | 23.0M/41.5M [03:41<03:13, 100kB/s]
+ 55%|#####5 | 23.0M/41.5M [03:42<03:17, 97.9kB/s]
+ 56%|#####5 | 23.0M/41.5M [03:42<03:21, 96.2kB/s]
+ 56%|#####5 | 23.0M/41.5M [03:42<03:07, 103kB/s]
+ 56%|#####5 | 23.1M/41.5M [03:42<03:02, 106kB/s]
+ 56%|#####5 | 23.1M/41.5M [03:42<03:23, 95.0kB/s]
+ 56%|#####5 | 23.1M/41.5M [03:43<02:59, 107kB/s]
+ 56%|#####5 | 23.1M/41.5M [03:43<03:06, 103kB/s]
+ 56%|#####5 | 23.1M/41.5M [03:43<03:12, 99.9kB/s]
+ 56%|#####5 | 23.2M/41.5M [03:43<03:30, 91.4kB/s]
+ 56%|#####5 | 23.2M/41.5M [03:43<02:51, 112kB/s]
+ 56%|#####5 | 23.2M/41.5M [03:44<04:50, 66.0kB/s]
+ 56%|#####5 | 23.2M/41.5M [03:44<03:41, 86.3kB/s]
+ 56%|#####6 | 23.2M/41.5M [03:44<03:52, 82.2kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:44<03:46, 84.5kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:45<04:05, 77.9kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:45<03:54, 81.4kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:45<03:46, 84.1kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:45<03:56, 80.7kB/s]
+ 56%|#####6 | 23.3M/41.5M [03:45<03:47, 83.7kB/s]
+ 56%|#####6 | 23.4M/41.5M [03:46<05:26, 58.2kB/s]
+ 56%|#####6 | 23.4M/41.5M [03:46<03:44, 84.7kB/s]
+ 56%|#####6 | 23.4M/41.5M [03:46<03:51, 81.9kB/s]
+ 56%|#####6 | 23.4M/41.5M [03:47<03:44, 84.4kB/s]
+ 56%|#####6 | 23.4M/41.5M [03:47<03:39, 86.4kB/s]
+ 57%|#####6 | 23.4M/41.5M [03:47<03:35, 88.0kB/s]
+ 57%|#####6 | 23.5M/41.5M [03:47<03:32, 89.1kB/s]
+ 57%|#####6 | 23.5M/41.5M [03:47<03:15, 96.5kB/s]
+ 57%|#####6 | 23.5M/41.5M [03:47<03:18, 95.2kB/s]
+ 57%|#####6 | 23.5M/41.5M [03:48<03:19, 94.3kB/s]
+ 57%|#####6 | 23.5M/41.5M [03:48<04:37, 67.8kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:48<03:15, 96.0kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:48<03:30, 89.3kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:49<03:28, 90.1kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:49<03:26, 90.7kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:49<03:25, 91.0kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:49<03:10, 98.5kB/s]
+ 57%|#####6 | 23.6M/41.5M [03:49<03:13, 96.6kB/s]
+ 57%|#####7 | 23.7M/41.5M [03:50<04:30, 69.0kB/s]
+ 57%|#####7 | 23.7M/41.5M [03:50<03:36, 86.2kB/s]
+ 57%|#####7 | 23.7M/41.5M [03:50<03:32, 87.6kB/s]
+ 57%|#####7 | 23.7M/41.5M [03:50<03:29, 88.8kB/s]
+ 57%|#####7 | 23.7M/41.5M [03:50<03:27, 89.7kB/s]
+ 57%|#####7 | 23.8M/41.5M [03:51<03:25, 90.4kB/s]
+ 57%|#####7 | 23.8M/41.5M [03:51<03:24, 90.9kB/s]
+ 57%|#####7 | 23.8M/41.5M [03:51<04:21, 70.9kB/s]
+ 57%|#####7 | 23.8M/41.5M [03:51<04:23, 70.3kB/s]
+ 57%|#####7 | 23.8M/41.5M [03:52<03:37, 85.0kB/s]
+ 57%|#####7 | 23.9M/41.5M [03:52<04:23, 70.1kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:52<04:19, 71.1kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:52<04:26, 69.3kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:53<04:51, 63.4kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:53<04:19, 71.1kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:53<04:15, 72.0kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:53<04:24, 69.7kB/s]
+ 58%|#####7 | 23.9M/41.5M [03:53<04:01, 76.2kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:53<03:47, 81.0kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:54<03:37, 84.3kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:54<03:31, 86.7kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:54<03:27, 88.3kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:54<03:24, 89.5kB/s]
+ 58%|#####7 | 24.0M/41.5M [03:54<02:55, 104kB/s]
+ 58%|#####7 | 24.1M/41.5M [03:54<03:01, 101kB/s]
+ 58%|#####8 | 24.1M/41.5M [03:55<02:43, 112kB/s]
+ 58%|#####8 | 24.1M/41.5M [03:55<02:16, 134kB/s]
+ 58%|#####8 | 24.1M/41.5M [03:55<02:14, 135kB/s]
+ 58%|#####8 | 24.2M/41.5M [03:55<01:50, 164kB/s]
+ 58%|#####8 | 24.2M/41.5M [03:55<01:46, 170kB/s]
+ 58%|#####8 | 24.2M/41.5M [03:56<01:36, 188kB/s]
+ 59%|#####8 | 24.3M/41.5M [03:56<01:24, 215kB/s]
+ 59%|#####8 | 24.3M/41.5M [03:56<01:17, 233kB/s]
+ 59%|#####8 | 24.4M/41.5M [03:56<01:27, 204kB/s]
+ 59%|#####8 | 24.4M/41.5M [03:56<01:19, 226kB/s]
+ 59%|#####8 | 24.5M/41.5M [03:56<01:06, 269kB/s]
+ 59%|#####9 | 24.5M/41.5M [03:57<01:35, 187kB/s]
+ 59%|#####9 | 24.6M/41.5M [03:57<01:06, 266kB/s]
+ 59%|#####9 | 24.6M/41.5M [03:57<01:12, 245kB/s]
+ 59%|#####9 | 24.6M/41.5M [03:57<01:17, 229kB/s]
+ 59%|#####9 | 24.7M/41.5M [03:58<01:26, 203kB/s]
+ 60%|#####9 | 24.7M/41.5M [03:58<01:23, 211kB/s]
+ 60%|#####9 | 24.7M/41.5M [03:58<01:32, 190kB/s]
+ 60%|#####9 | 24.8M/41.5M [03:58<01:38, 178kB/s]
+ 60%|#####9 | 24.8M/41.5M [03:58<02:19, 126kB/s]
+ 60%|#####9 | 24.8M/41.5M [03:59<02:05, 140kB/s]
+ 60%|#####9 | 24.9M/41.5M [03:59<01:49, 160kB/s]
+ 60%|###### | 24.9M/41.5M [03:59<01:59, 146kB/s]
+ 60%|###### | 24.9M/41.5M [03:59<02:10, 133kB/s]
+ 60%|###### | 24.9M/41.5M [04:00<02:21, 123kB/s]
+ 60%|###### | 24.9M/41.5M [04:00<02:31, 114kB/s]
+ 60%|###### | 25.0M/41.5M [04:00<02:29, 116kB/s]
+ 60%|###### | 25.0M/41.5M [04:00<02:38, 109kB/s]
+ 60%|###### | 25.0M/41.5M [04:00<02:26, 118kB/s]
+ 60%|###### | 25.0M/41.5M [04:00<02:36, 110kB/s]
+ 60%|###### | 25.0M/41.5M [04:01<02:25, 119kB/s]
+ 60%|###### | 25.1M/41.5M [04:01<02:58, 96.6kB/s]
+ 60%|###### | 25.1M/41.5M [04:01<03:37, 79.0kB/s]
+ 61%|###### | 25.1M/41.5M [04:01<02:34, 111kB/s]
+ 61%|###### | 25.1M/41.5M [04:02<03:03, 93.8kB/s]
+ 61%|###### | 25.1M/41.5M [04:02<02:52, 99.5kB/s]
+ 61%|###### | 25.1M/41.5M [04:02<02:55, 97.5kB/s]
+ 61%|###### | 25.2M/41.5M [04:02<03:10, 89.9kB/s]
+ 61%|###### | 25.2M/41.5M [04:02<03:09, 90.5kB/s]
+ 61%|###### | 25.2M/41.5M [04:03<04:41, 60.7kB/s]
+ 61%|###### | 25.2M/41.5M [04:03<03:26, 82.8kB/s]
+ 61%|###### | 25.2M/41.5M [04:03<03:20, 84.9kB/s]
+ 61%|###### | 25.3M/41.5M [04:03<03:16, 86.7kB/s]
+ 61%|###### | 25.3M/41.5M [04:03<03:13, 88.0kB/s]
+ 61%|###### | 25.3M/41.5M [04:04<03:10, 89.3kB/s]
+ 61%|###### | 25.3M/41.5M [04:04<03:08, 90.1kB/s]
+ 61%|######1 | 25.3M/41.5M [04:04<04:53, 57.8kB/s]
+ 61%|######1 | 25.3M/41.5M [04:05<04:34, 61.6kB/s]
+ 61%|######1 | 25.4M/41.5M [04:05<03:40, 76.6kB/s]
+ 61%|######1 | 25.4M/41.5M [04:05<04:28, 62.9kB/s]
+ 61%|######1 | 25.4M/41.5M [04:05<04:29, 62.6kB/s]
+ 61%|######1 | 25.4M/41.5M [04:06<05:52, 47.9kB/s]
+ 61%|######1 | 25.4M/41.5M [04:06<04:54, 57.2kB/s]
+ 61%|######1 | 25.4M/41.5M [04:06<05:08, 54.7kB/s]
+ 61%|######1 | 25.4M/41.5M [04:06<04:23, 63.9kB/s]
+ 61%|######1 | 25.4M/41.5M [04:06<04:43, 59.4kB/s]
+ 61%|######1 | 25.5M/41.5M [04:07<05:01, 55.8kB/s]
+ 61%|######1 | 25.5M/41.5M [04:07<05:16, 53.1kB/s]
+ 61%|######1 | 25.5M/41.5M [04:07<04:21, 64.1kB/s]
+ 61%|######1 | 25.5M/41.5M [04:07<04:44, 59.0kB/s]
+ 61%|######1 | 25.5M/41.5M [04:07<04:04, 68.6kB/s]
+ 61%|######1 | 25.5M/41.5M [04:08<04:29, 62.1kB/s]
+ 61%|######1 | 25.5M/41.5M [04:08<06:19, 44.1kB/s]
+ 62%|######1 | 25.5M/41.5M [04:08<06:10, 45.1kB/s]
+ 62%|######1 | 25.6M/41.5M [04:09<06:06, 45.5kB/s]
+ 62%|######1 | 25.6M/41.5M [04:09<04:34, 60.8kB/s]
+ 62%|######1 | 25.6M/41.5M [04:09<04:47, 58.0kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<05:00, 55.5kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<05:12, 53.3kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<05:23, 51.5kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<05:32, 50.1kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<04:29, 61.6kB/s]
+ 62%|######1 | 25.6M/41.5M [04:10<04:50, 57.3kB/s]
+ 62%|######1 | 25.7M/41.5M [04:11<05:06, 54.1kB/s]
+ 62%|######1 | 25.7M/41.5M [04:11<06:53, 40.1kB/s]
+ 62%|######1 | 25.7M/41.5M [04:11<04:18, 64.0kB/s]
+ 62%|######1 | 25.7M/41.5M [04:11<03:52, 71.3kB/s]
+ 62%|######1 | 25.7M/41.5M [04:11<04:16, 64.5kB/s]
+ 62%|######2 | 25.7M/41.5M [04:12<03:48, 72.2kB/s]
+ 62%|######2 | 25.7M/41.5M [04:12<03:31, 77.9kB/s]
+ 62%|######2 | 25.8M/41.5M [04:12<04:00, 68.7kB/s]
+ 62%|######2 | 25.8M/41.5M [04:12<03:38, 75.6kB/s]
+ 62%|######2 | 25.8M/41.5M [04:12<03:24, 80.5kB/s]
+ 62%|######2 | 25.8M/41.5M [04:13<03:15, 84.0kB/s]
+ 62%|######2 | 25.8M/41.5M [04:13<03:10, 86.4kB/s]
+ 62%|######2 | 25.8M/41.5M [04:13<03:06, 88.1kB/s]
+ 62%|######2 | 25.8M/41.5M [04:13<03:03, 89.4kB/s]
+ 62%|######2 | 25.9M/41.5M [04:13<03:01, 90.3kB/s]
+ 62%|######2 | 25.9M/41.5M [04:13<03:00, 90.9kB/s]
+ 62%|######2 | 25.9M/41.5M [04:14<02:59, 91.3kB/s]
+ 62%|######2 | 25.9M/41.5M [04:14<02:35, 105kB/s]
+ 62%|######2 | 25.9M/41.5M [04:14<02:40, 101kB/s]
+ 63%|######2 | 26.0M/41.5M [04:14<02:24, 112kB/s]
+ 63%|######2 | 26.0M/41.5M [04:14<02:32, 106kB/s]
+ 63%|######2 | 26.0M/41.5M [04:14<02:20, 116kB/s]
+ 63%|######2 | 26.0M/41.5M [04:15<02:12, 123kB/s]
+ 63%|######2 | 26.0M/41.5M [04:15<02:07, 127kB/s]
+ 63%|######2 | 26.1M/41.5M [04:15<02:03, 131kB/s]
+ 63%|######2 | 26.1M/41.5M [04:15<02:01, 133kB/s]
+ 63%|######2 | 26.1M/41.5M [04:15<01:59, 135kB/s]
+ 63%|######2 | 26.1M/41.5M [04:16<01:58, 136kB/s]
+ 63%|######3 | 26.2M/41.5M [04:16<02:19, 115kB/s]
+ 63%|######3 | 26.2M/41.5M [04:16<02:31, 106kB/s]
+ 63%|######3 | 26.2M/41.5M [04:16<01:51, 144kB/s]
+ 63%|######3 | 26.3M/41.5M [04:17<02:30, 106kB/s]
+ 63%|######3 | 26.3M/41.5M [04:17<02:37, 101kB/s]
+ 63%|######3 | 26.3M/41.5M [04:17<02:40, 99.2kB/s]
+ 63%|######3 | 26.3M/41.5M [04:18<02:27, 108kB/s]
+ 63%|######3 | 26.3M/41.5M [04:18<02:32, 104kB/s]
+ 64%|######3 | 26.4M/41.5M [04:18<02:36, 101kB/s]
+ 64%|######3 | 26.4M/41.5M [04:18<02:40, 98.7kB/s]
+ 64%|######3 | 26.4M/41.5M [04:18<03:05, 85.4kB/s]
+ 64%|######3 | 26.4M/41.5M [04:19<03:25, 76.9kB/s]
+ 64%|######3 | 26.4M/41.5M [04:19<06:35, 39.9kB/s]
+ 64%|######3 | 26.5M/41.5M [04:20<03:12, 81.8kB/s]
+ 64%|######3 | 26.5M/41.5M [04:20<02:51, 91.7kB/s]
+ 64%|######3 | 26.5M/41.5M [04:20<02:35, 101kB/s]
+ 64%|######3 | 26.5M/41.5M [04:20<02:23, 109kB/s]
+ 64%|######4 | 26.6M/41.5M [04:20<02:14, 116kB/s]
+ 64%|######4 | 26.6M/41.5M [04:21<02:40, 97.1kB/s]
+ 64%|######4 | 26.6M/41.5M [04:21<01:53, 138kB/s]
+ 64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
+ 64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
+ 64%|######4 | 26.7M/41.5M [04:21<01:52, 138kB/s]
+ 64%|######4 | 26.7M/41.5M [04:22<01:52, 138kB/s]
+ 64%|######4 | 26.8M/41.5M [04:22<02:23, 107kB/s]
+ 65%|######4 | 26.8M/41.5M [04:22<01:43, 148kB/s]
+ 65%|######4 | 26.8M/41.5M [04:22<01:45, 146kB/s]
+ 65%|######4 | 26.8M/41.5M [04:23<02:28, 104kB/s]
+ 65%|######4 | 26.9M/41.5M [04:23<01:46, 144kB/s]
+ 65%|######4 | 26.9M/41.5M [04:23<01:47, 142kB/s]
+ 65%|######4 | 26.9M/41.5M [04:23<02:29, 102kB/s]
+ 65%|######4 | 26.9M/41.5M [04:24<02:32, 100kB/s]
+ 65%|######5 | 27.0M/41.5M [04:24<02:05, 121kB/s]
+ 65%|######5 | 27.0M/41.5M [04:24<02:14, 113kB/s]
+ 65%|######5 | 27.0M/41.5M [04:24<02:20, 108kB/s]
+ 65%|######5 | 27.0M/41.5M [04:24<02:10, 116kB/s]
+ 65%|######5 | 27.0M/41.5M [04:24<02:18, 109kB/s]
+ 65%|######5 | 27.1M/41.5M [04:25<02:08, 118kB/s]
+ 65%|######5 | 27.1M/41.5M [04:25<02:01, 124kB/s]
+ 65%|######5 | 27.1M/41.5M [04:25<02:11, 115kB/s]
+ 65%|######5 | 27.1M/41.5M [04:25<02:03, 122kB/s]
+ 65%|######5 | 27.2M/41.5M [04:25<01:58, 127kB/s]
+ 65%|######5 | 27.2M/41.5M [04:26<02:47, 89.5kB/s]
+ 66%|######5 | 27.2M/41.5M [04:26<02:00, 124kB/s]
+ 66%|######5 | 27.2M/41.5M [04:26<02:08, 116kB/s]
+ 66%|######5 | 27.2M/41.5M [04:26<02:16, 110kB/s]
+ 66%|######5 | 27.3M/41.5M [04:26<02:06, 118kB/s]
+ 66%|######5 | 27.3M/41.5M [04:27<02:14, 110kB/s]
+ 66%|######5 | 27.3M/41.5M [04:27<02:05, 118kB/s]
+ 66%|######5 | 27.3M/41.5M [04:27<01:59, 124kB/s]
+ 66%|######5 | 27.4M/41.5M [04:27<01:55, 128kB/s]
+ 66%|######5 | 27.4M/41.5M [04:27<01:52, 131kB/s]
+ 66%|######6 | 27.4M/41.5M [04:27<02:03, 120kB/s]
+ 66%|######6 | 27.4M/41.5M [04:28<01:57, 125kB/s]
+ 66%|######6 | 27.4M/41.5M [04:28<01:54, 129kB/s]
+ 66%|######6 | 27.5M/41.5M [04:28<01:51, 132kB/s]
+ 66%|######6 | 27.5M/41.5M [04:28<01:49, 134kB/s]
+ 66%|######6 | 27.5M/41.5M [04:28<01:48, 135kB/s]
+ 66%|######6 | 27.5M/41.5M [04:29<01:47, 136kB/s]
+ 66%|######6 | 27.6M/41.5M [04:29<01:36, 151kB/s]
+ 66%|######6 | 27.6M/41.5M [04:29<01:39, 147kB/s]
+ 67%|######6 | 27.6M/41.5M [04:29<01:40, 144kB/s]
+ 67%|######6 | 27.6M/41.5M [04:29<01:32, 156kB/s]
+ 67%|######6 | 27.7M/41.5M [04:29<01:27, 165kB/s]
+ 67%|######6 | 27.7M/41.5M [04:30<01:59, 121kB/s]
+ 67%|######6 | 27.8M/41.5M [04:30<01:55, 124kB/s]
+ 67%|######6 | 27.8M/41.5M [04:30<01:33, 154kB/s]
+ 67%|######7 | 27.8M/41.5M [04:31<01:41, 142kB/s]
+ 67%|######7 | 27.8M/41.5M [04:31<01:50, 130kB/s]
+ 67%|######7 | 27.8M/41.5M [04:31<01:51, 128kB/s]
+ 67%|######7 | 27.9M/41.5M [04:31<02:00, 118kB/s]
+ 67%|######7 | 27.9M/41.5M [04:31<01:59, 120kB/s]
+ 67%|######7 | 27.9M/41.5M [04:31<01:58, 121kB/s]
+ 67%|######7 | 27.9M/41.5M [04:32<02:07, 112kB/s]
+ 67%|######7 | 27.9M/41.5M [04:32<02:04, 114kB/s]
+ 67%|######7 | 27.9M/41.5M [04:32<02:02, 116kB/s]
+ 67%|######7 | 28.0M/41.5M [04:32<01:59, 119kB/s]
+ 67%|######7 | 28.0M/41.5M [04:32<01:58, 120kB/s]
+ 67%|######7 | 28.0M/41.5M [04:32<02:42, 87.0kB/s]
+ 68%|######7 | 28.0M/41.5M [04:33<01:54, 123kB/s]
+ 68%|######7 | 28.0M/41.5M [04:33<02:04, 114kB/s]
+ 68%|######7 | 28.0M/41.5M [04:33<02:51, 82.3kB/s]
+ 68%|######7 | 28.1M/41.5M [04:33<02:20, 100kB/s]
+ 68%|######7 | 28.1M/41.5M [04:33<02:29, 94.0kB/s]
+ 68%|######7 | 28.1M/41.5M [04:34<02:30, 93.5kB/s]
+ 68%|######7 | 28.1M/41.5M [04:34<02:30, 93.0kB/s]
+ 68%|######7 | 28.1M/41.5M [04:34<02:30, 92.8kB/s]
+ 68%|######7 | 28.2M/41.5M [04:34<03:13, 72.2kB/s]
+ 68%|######7 | 28.2M/41.5M [04:35<02:38, 88.0kB/s]
+ 68%|######7 | 28.2M/41.5M [04:35<02:51, 81.3kB/s]
+ 68%|######7 | 28.2M/41.5M [04:35<02:45, 84.0kB/s]
+ 68%|######8 | 28.2M/41.5M [04:35<02:41, 86.2kB/s]
+ 68%|######8 | 28.2M/41.5M [04:35<02:38, 87.8kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:35, 89.1kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:34, 90.0kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:51, 80.7kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:44, 83.8kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:21, 97.7kB/s]
+ 68%|######8 | 28.3M/41.5M [04:36<02:23, 96.1kB/s]
+ 68%|######8 | 28.4M/41.5M [04:37<02:19, 98.8kB/s]
+ 68%|######8 | 28.4M/41.5M [04:37<02:22, 96.7kB/s]
+ 68%|######8 | 28.4M/41.5M [04:37<02:12, 103kB/s]
+ 68%|######8 | 28.4M/41.5M [04:37<02:08, 106kB/s]
+ 68%|######8 | 28.4M/41.5M [04:37<01:55, 118kB/s]
+ 69%|######8 | 28.4M/41.5M [04:37<01:59, 114kB/s]
+ 69%|######8 | 28.4M/41.5M [04:37<01:56, 117kB/s]
+ 69%|######8 | 28.5M/41.5M [04:38<01:50, 124kB/s]
+ 69%|######8 | 28.5M/41.5M [04:38<01:49, 124kB/s]
+ 69%|######8 | 28.5M/41.5M [04:38<02:45, 82.3kB/s]
+ 69%|######8 | 28.5M/41.5M [04:38<02:29, 91.0kB/s]
+ 69%|######8 | 28.5M/41.5M [04:38<01:44, 130kB/s]
+ 69%|######8 | 28.6M/41.5M [04:39<02:29, 90.9kB/s]
+ 69%|######8 | 28.6M/41.5M [04:39<02:03, 110kB/s]
+ 69%|######8 | 28.6M/41.5M [04:39<02:08, 105kB/s]
+ 69%|######8 | 28.6M/41.5M [04:39<02:39, 84.8kB/s]
+ 69%|######9 | 28.6M/41.5M [04:39<02:35, 86.7kB/s]
+ 69%|######9 | 28.6M/41.5M [04:40<02:41, 83.5kB/s]
+ 69%|######9 | 28.7M/41.5M [04:40<02:36, 85.8kB/s]
+ 69%|######9 | 28.7M/41.5M [04:40<02:24, 93.0kB/s]
+ 69%|######9 | 28.7M/41.5M [04:40<02:24, 92.8kB/s]
+ 69%|######9 | 28.7M/41.5M [04:40<02:24, 92.6kB/s]
+ 69%|######9 | 28.7M/41.5M [04:41<02:13, 99.8kB/s]
+ 69%|######9 | 28.8M/41.5M [04:41<02:08, 104kB/s]
+ 69%|######9 | 28.8M/41.5M [04:41<02:04, 107kB/s]
+ 69%|######9 | 28.8M/41.5M [04:41<02:01, 110kB/s]
+ 69%|######9 | 28.8M/41.5M [04:41<01:59, 111kB/s]
+ 70%|######9 | 28.8M/41.5M [04:41<01:51, 119kB/s]
+ 70%|######9 | 28.9M/41.5M [04:42<01:46, 125kB/s]
+ 70%|######9 | 28.9M/41.5M [04:42<01:47, 123kB/s]
+ 70%|######9 | 28.9M/41.5M [04:42<01:43, 128kB/s]
+ 70%|######9 | 28.9M/41.5M [04:42<02:18, 95.3kB/s]
+ 70%|######9 | 29.0M/41.5M [04:43<01:34, 139kB/s]
+ 70%|######9 | 29.0M/41.5M [04:43<01:43, 127kB/s]
+ 70%|######9 | 29.0M/41.5M [04:43<01:40, 130kB/s]
+ 70%|######9 | 29.0M/41.5M [04:43<01:38, 132kB/s]
+ 70%|####### | 29.0M/41.5M [04:43<01:50, 118kB/s]
+ 70%|####### | 29.1M/41.5M [04:43<01:42, 127kB/s]
+ 70%|####### | 29.1M/41.5M [04:44<02:19, 93.4kB/s]
+ 70%|####### | 29.1M/41.5M [04:44<01:46, 122kB/s]
+ 70%|####### | 29.1M/41.5M [04:44<01:53, 114kB/s]
+ 70%|####### | 29.2M/41.5M [04:44<01:59, 108kB/s]
+ 70%|####### | 29.2M/41.5M [04:45<02:36, 82.6kB/s]
+ 70%|####### | 29.2M/41.5M [04:45<03:08, 68.3kB/s]
+ 70%|####### | 29.2M/41.5M [04:45<02:34, 83.5kB/s]
+ 70%|####### | 29.2M/41.5M [04:46<03:05, 69.2kB/s]
+ 70%|####### | 29.2M/41.5M [04:46<02:53, 74.2kB/s]
+ 71%|####### | 29.3M/41.5M [04:46<02:46, 77.0kB/s]
+ 71%|####### | 29.3M/41.5M [04:46<03:57, 54.0kB/s]
+ 71%|####### | 29.3M/41.5M [04:47<04:45, 44.8kB/s]
+ 71%|####### | 29.3M/41.5M [04:48<04:41, 45.3kB/s]
+ 71%|####### | 29.3M/41.5M [04:48<03:34, 59.4kB/s]
+ 71%|####### | 29.3M/41.5M [04:48<03:43, 57.0kB/s]
+ 71%|####### | 29.4M/41.5M [04:48<05:29, 38.6kB/s]
+ 71%|####### | 29.4M/41.5M [04:49<04:23, 48.3kB/s]
+ 71%|####### | 29.4M/41.5M [04:49<06:09, 34.4kB/s]
+ 71%|####### | 29.4M/41.5M [04:49<05:36, 37.7kB/s]
+ 71%|####### | 29.4M/41.5M [04:50<05:23, 39.2kB/s]
+ 71%|####### | 29.4M/41.5M [04:50<05:12, 40.5kB/s]
+ 71%|####### | 29.4M/41.5M [04:50<05:03, 41.8kB/s]
+ 71%|####### | 29.4M/41.5M [04:50<04:55, 42.8kB/s]
+ 71%|####### | 29.4M/41.5M [04:50<04:49, 43.6kB/s]
+ 71%|####### | 29.4M/41.5M [04:51<04:45, 44.3kB/s]
+ 71%|####### | 29.4M/41.5M [04:51<04:41, 44.8kB/s]
+ 71%|####### | 29.5M/41.5M [04:51<04:39, 45.2kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:51<04:37, 45.5kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:51<03:33, 59.1kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:51<03:47, 55.3kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:52<03:09, 66.2kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:52<02:49, 73.9kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:52<03:11, 65.7kB/s]
+ 71%|#######1 | 29.5M/41.5M [04:52<02:50, 73.6kB/s]
+ 71%|#######1 | 29.6M/41.5M [04:52<02:38, 79.2kB/s]
+ 71%|#######1 | 29.6M/41.5M [04:52<02:08, 96.9kB/s]
+ 71%|#######1 | 29.6M/41.5M [04:53<01:54, 109kB/s]
+ 71%|#######1 | 29.6M/41.5M [04:53<01:45, 118kB/s]
+ 71%|#######1 | 29.6M/41.5M [04:53<01:40, 124kB/s]
+ 72%|#######1 | 29.7M/41.5M [04:53<01:27, 142kB/s]
+ 72%|#######1 | 29.7M/41.5M [04:53<01:13, 169kB/s]
+ 72%|#######1 | 29.8M/41.5M [04:54<01:05, 187kB/s]
+ 72%|#######1 | 29.8M/41.5M [04:54<00:57, 214kB/s]
+ 72%|#######1 | 29.9M/41.5M [04:54<00:49, 247kB/s]
+ 72%|#######2 | 29.9M/41.5M [04:54<00:53, 227kB/s]
+ 72%|#######2 | 30.0M/41.5M [04:54<00:42, 284kB/s]
+ 72%|#######2 | 30.0M/41.5M [04:54<00:44, 268kB/s]
+ 72%|#######2 | 30.0M/41.5M [04:55<00:44, 271kB/s]
+ 73%|#######2 | 30.1M/41.5M [04:55<00:43, 272kB/s]
+ 73%|#######2 | 30.1M/41.5M [04:55<00:41, 288kB/s]
+ 73%|#######2 | 30.2M/41.5M [04:55<00:41, 284kB/s]
+ 73%|#######2 | 30.2M/41.5M [04:55<00:46, 254kB/s]
+ 73%|#######3 | 30.3M/41.5M [04:55<00:40, 288kB/s]
+ 73%|#######3 | 30.3M/41.5M [04:56<00:59, 198kB/s]
+ 73%|#######3 | 30.4M/41.5M [04:56<00:44, 263kB/s]
+ 73%|#######3 | 30.4M/41.5M [04:56<00:47, 242kB/s]
+ 73%|#######3 | 30.5M/41.5M [04:56<00:51, 227kB/s]
+ 73%|#######3 | 30.5M/41.5M [04:57<00:53, 215kB/s]
+ 74%|#######3 | 30.5M/41.5M [04:57<01:16, 150kB/s]
+ 74%|#######3 | 30.6M/41.5M [04:57<00:53, 214kB/s]
+ 74%|#######3 | 30.6M/41.5M [04:57<00:55, 206kB/s]
+ 74%|#######3 | 30.6M/41.5M [04:57<01:00, 188kB/s]
+ 74%|#######3 | 30.7M/41.5M [04:58<01:05, 174kB/s]
+ 74%|#######3 | 30.7M/41.5M [04:58<01:03, 177kB/s]
+ 74%|#######4 | 30.7M/41.5M [04:58<01:27, 129kB/s]
+ 74%|#######4 | 30.8M/41.5M [04:58<01:00, 187kB/s]
+ 74%|#######4 | 30.8M/41.5M [04:59<01:04, 174kB/s]
+ 74%|#######4 | 30.8M/41.5M [04:59<01:07, 165kB/s]
+ 74%|#######4 | 30.9M/41.5M [04:59<01:10, 157kB/s]
+ 74%|#######4 | 30.9M/41.5M [04:59<01:13, 152kB/s]
+ 74%|#######4 | 30.9M/41.5M [04:59<01:08, 161kB/s]
+ 75%|#######4 | 30.9M/41.5M [04:59<01:11, 155kB/s]
+ 75%|#######4 | 31.0M/41.5M [05:00<01:07, 163kB/s]
+ 75%|#######4 | 31.0M/41.5M [05:00<01:10, 156kB/s]
+ 75%|#######4 | 31.0M/41.5M [05:00<01:12, 151kB/s]
+ 75%|#######4 | 31.0M/41.5M [05:00<01:08, 161kB/s]
+ 75%|#######4 | 31.1M/41.5M [05:01<01:47, 102kB/s]
+ 75%|#######5 | 31.1M/41.5M [05:01<00:58, 187kB/s]
+ 75%|#######5 | 31.2M/41.5M [05:01<01:29, 122kB/s]
+ 75%|#######5 | 31.2M/41.5M [05:01<01:10, 152kB/s]
+ 75%|#######5 | 31.2M/41.5M [05:02<01:12, 149kB/s]
+ 75%|#######5 | 31.2M/41.5M [05:02<01:30, 118kB/s]
+ 75%|#######5 | 31.3M/41.5M [05:02<02:16, 78.5kB/s]
+ 75%|#######5 | 31.3M/41.5M [05:03<02:21, 75.7kB/s]
+ 76%|#######5 | 31.4M/41.5M [05:04<02:07, 83.3kB/s]
+ 76%|#######5 | 31.4M/41.5M [05:04<01:30, 117kB/s]
+ 76%|#######5 | 31.4M/41.5M [05:04<01:42, 103kB/s]
+ 76%|#######5 | 31.4M/41.5M [05:04<01:43, 102kB/s]
+ 76%|#######5 | 31.5M/41.5M [05:05<02:29, 70.4kB/s]
+ 76%|#######5 | 31.5M/41.5M [05:05<01:55, 91.0kB/s]
+ 76%|#######5 | 31.5M/41.5M [05:05<02:39, 65.8kB/s]
+ 76%|#######5 | 31.5M/41.5M [05:06<02:14, 77.9kB/s]
+ 76%|#######6 | 31.5M/41.5M [05:06<02:09, 80.5kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:06<02:32, 68.4kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:06<02:21, 73.3kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:07<02:14, 77.4kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:07<02:07, 81.0kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:07<02:34, 66.8kB/s]
+ 76%|#######6 | 31.6M/41.5M [05:07<02:22, 72.6kB/s]
+ 76%|#######6 | 31.7M/41.5M [05:07<02:13, 77.4kB/s]
+ 76%|#######6 | 31.7M/41.5M [05:08<02:06, 81.2kB/s]
+ 76%|#######6 | 31.7M/41.5M [05:08<02:02, 84.2kB/s]
+ 76%|#######6 | 31.7M/41.5M [05:08<01:43, 99.2kB/s]
+ 76%|#######6 | 31.7M/41.5M [05:08<01:45, 97.3kB/s]
+ 77%|#######6 | 31.7M/41.5M [05:08<01:46, 95.8kB/s]
+ 77%|#######6 | 31.8M/41.5M [05:08<01:47, 94.8kB/s]
+ 77%|#######6 | 31.8M/41.5M [05:09<01:48, 94.1kB/s]
+ 77%|#######6 | 31.8M/41.5M [05:09<01:34, 107kB/s]
+ 77%|#######6 | 31.8M/41.5M [05:09<01:38, 103kB/s]
+ 77%|#######6 | 31.8M/41.5M [05:09<01:29, 113kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:09<01:34, 107kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:10<01:38, 103kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:10<01:28, 113kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:10<01:33, 107kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:10<01:37, 103kB/s]
+ 77%|#######6 | 31.9M/41.5M [05:10<01:40, 99.4kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:10<01:42, 97.3kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:11<01:44, 95.8kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:11<01:45, 94.7kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:11<01:32, 108kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:11<01:36, 103kB/s]
+ 77%|#######7 | 32.0M/41.5M [05:11<01:39, 99.9kB/s]
+ 77%|#######7 | 32.1M/41.5M [05:11<01:28, 111kB/s]
+ 77%|#######7 | 32.1M/41.5M [05:12<01:33, 106kB/s]
+ 77%|#######7 | 32.1M/41.5M [05:12<01:25, 115kB/s]
+ 77%|#######7 | 32.1M/41.5M [05:12<01:30, 109kB/s]
+ 77%|#######7 | 32.1M/41.5M [05:12<01:23, 117kB/s]
+ 78%|#######7 | 32.2M/41.5M [05:12<01:29, 110kB/s]
+ 78%|#######7 | 32.2M/41.5M [05:13<01:47, 91.1kB/s]
+ 78%|#######7 | 32.2M/41.5M [05:13<01:17, 126kB/s]
+ 78%|#######7 | 32.2M/41.5M [05:13<01:22, 117kB/s]
+ 78%|#######7 | 32.2M/41.5M [05:13<01:27, 110kB/s]
+ 78%|#######7 | 32.3M/41.5M [05:13<01:31, 105kB/s]
+ 78%|#######7 | 32.3M/41.5M [05:14<01:48, 89.2kB/s]
+ 78%|#######7 | 32.3M/41.5M [05:14<01:18, 123kB/s]
+ 78%|#######7 | 32.3M/41.5M [05:14<01:23, 115kB/s]
+ 78%|#######7 | 32.4M/41.5M [05:14<01:27, 109kB/s]
+ 78%|#######8 | 32.4M/41.5M [05:15<01:21, 117kB/s]
+ 78%|#######8 | 32.4M/41.5M [05:15<01:17, 123kB/s]
+ 78%|#######8 | 32.4M/41.5M [05:15<01:14, 127kB/s]
+ 78%|#######8 | 32.4M/41.5M [05:15<01:20, 117kB/s]
+ 78%|#######8 | 32.5M/41.5M [05:15<01:16, 124kB/s]
+ 78%|#######8 | 32.5M/41.5M [05:15<01:13, 128kB/s]
+ 78%|#######8 | 32.5M/41.5M [05:16<01:11, 131kB/s]
+ 78%|#######8 | 32.5M/41.5M [05:16<01:10, 133kB/s]
+ 78%|#######8 | 32.6M/41.5M [05:16<01:28, 106kB/s]
+ 79%|#######8 | 32.6M/41.5M [05:16<01:16, 123kB/s]
+ 79%|#######8 | 32.6M/41.5M [05:16<01:16, 122kB/s]
+ 79%|#######8 | 32.6M/41.5M [05:16<01:22, 113kB/s]
+ 79%|#######8 | 32.6M/41.5M [05:17<01:28, 105kB/s]
+ 79%|#######8 | 32.7M/41.5M [05:17<01:21, 114kB/s]
+ 79%|#######8 | 32.7M/41.5M [05:17<01:16, 121kB/s]
+ 79%|#######8 | 32.7M/41.5M [05:17<01:13, 126kB/s]
+ 79%|#######8 | 32.7M/41.5M [05:17<01:18, 117kB/s]
+ 79%|#######8 | 32.7M/41.5M [05:18<01:14, 123kB/s]
+ 79%|#######8 | 32.8M/41.5M [05:18<01:11, 127kB/s]
+ 79%|#######9 | 32.8M/41.5M [05:18<01:09, 130kB/s]
+ 79%|#######9 | 32.8M/41.5M [05:18<01:08, 133kB/s]
+ 79%|#######9 | 32.8M/41.5M [05:18<01:14, 121kB/s]
+ 79%|#######9 | 32.8M/41.5M [05:19<01:33, 97.1kB/s]
+ 79%|#######9 | 32.9M/41.5M [05:19<01:07, 133kB/s]
+ 79%|#######9 | 32.9M/41.5M [05:19<01:08, 132kB/s]
+ 79%|#######9 | 32.9M/41.5M [05:19<01:09, 129kB/s]
+ 79%|#######9 | 32.9M/41.5M [05:19<01:16, 118kB/s]
+ 79%|#######9 | 32.9M/41.5M [05:19<01:34, 94.4kB/s]
+ 79%|#######9 | 33.0M/41.5M [05:20<01:19, 112kB/s]
+ 80%|#######9 | 33.0M/41.5M [05:20<01:23, 107kB/s]
+ 80%|#######9 | 33.0M/41.5M [05:20<01:26, 103kB/s]
+ 80%|#######9 | 33.0M/41.5M [05:20<01:18, 113kB/s]
+ 80%|#######9 | 33.0M/41.5M [05:20<01:22, 107kB/s]
+ 80%|#######9 | 33.1M/41.5M [05:21<01:20, 109kB/s]
+ 80%|#######9 | 33.1M/41.5M [05:21<01:24, 104kB/s]
+ 80%|#######9 | 33.1M/41.5M [05:21<01:21, 108kB/s]
+ 80%|#######9 | 33.1M/41.5M [05:21<01:19, 110kB/s]
+ 80%|#######9 | 33.1M/41.5M [05:21<01:18, 111kB/s]
+ 80%|#######9 | 33.2M/41.5M [05:21<01:22, 106kB/s]
+ 80%|#######9 | 33.2M/41.5M [05:22<01:15, 115kB/s]
+ 80%|######## | 33.2M/41.5M [05:22<01:20, 108kB/s]
+ 80%|######## | 33.2M/41.5M [05:22<01:18, 111kB/s]
+ 80%|######## | 33.2M/41.5M [05:22<01:15, 115kB/s]
+ 80%|######## | 33.2M/41.5M [05:22<01:33, 92.5kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:27, 98.6kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:29, 96.3kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:30, 95.5kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:30, 94.5kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:31, 93.8kB/s]
+ 80%|######## | 33.3M/41.5M [05:23<01:31, 93.4kB/s]
+ 80%|######## | 33.4M/41.5M [05:24<01:31, 93.0kB/s]
+ 80%|######## | 33.4M/41.5M [05:24<01:24, 101kB/s]
+ 80%|######## | 33.4M/41.5M [05:24<01:21, 104kB/s]
+ 81%|######## | 33.4M/41.5M [05:24<01:17, 109kB/s]
+ 81%|######## | 33.4M/41.5M [05:24<01:17, 109kB/s]
+ 81%|######## | 33.4M/41.5M [05:25<01:38, 85.9kB/s]
+ 81%|######## | 33.5M/41.5M [05:25<01:12, 116kB/s]
+ 81%|######## | 33.5M/41.5M [05:25<01:16, 110kB/s]
+ 81%|######## | 33.5M/41.5M [05:25<01:14, 112kB/s]
+ 81%|######## | 33.5M/41.5M [05:25<01:18, 106kB/s]
+ 81%|######## | 33.6M/41.5M [05:25<01:11, 116kB/s]
+ 81%|######## | 33.6M/41.5M [05:26<01:16, 109kB/s]
+ 81%|######## | 33.6M/41.5M [05:26<01:10, 118kB/s]
+ 81%|########1 | 33.6M/41.5M [05:26<01:09, 118kB/s]
+ 81%|########1 | 33.6M/41.5M [05:26<01:10, 116kB/s]
+ 81%|########1 | 33.7M/41.5M [05:26<01:06, 123kB/s]
+ 81%|########1 | 33.7M/41.5M [05:27<01:04, 127kB/s]
+ 81%|########1 | 33.7M/41.5M [05:27<01:09, 117kB/s]
+ 81%|########1 | 33.7M/41.5M [05:27<01:25, 95.3kB/s]
+ 81%|########1 | 33.7M/41.5M [05:27<01:03, 128kB/s]
+ 81%|########1 | 33.8M/41.5M [05:27<01:08, 118kB/s]
+ 81%|########1 | 33.8M/41.5M [05:27<01:08, 119kB/s]
+ 81%|########1 | 33.8M/41.5M [05:28<01:13, 110kB/s]
+ 81%|########1 | 33.8M/41.5M [05:28<01:07, 119kB/s]
+ 82%|########1 | 33.8M/41.5M [05:28<01:04, 125kB/s]
+ 82%|########1 | 33.9M/41.5M [05:28<01:30, 88.0kB/s]
+ 82%|########1 | 33.9M/41.5M [05:29<01:11, 112kB/s]
+ 82%|########1 | 33.9M/41.5M [05:29<01:14, 107kB/s]
+ 82%|########1 | 33.9M/41.5M [05:29<01:17, 103kB/s]
+ 82%|########1 | 33.9M/41.5M [05:29<01:10, 113kB/s]
+ 82%|########1 | 34.0M/41.5M [05:29<01:05, 120kB/s]
+ 82%|########1 | 34.0M/41.5M [05:29<01:10, 112kB/s]
+ 82%|########1 | 34.0M/41.5M [05:30<01:05, 120kB/s]
+ 82%|########2 | 34.0M/41.5M [05:30<01:02, 125kB/s]
+ 82%|########2 | 34.0M/41.5M [05:30<01:00, 129kB/s]
+ 82%|########2 | 34.1M/41.5M [05:30<00:58, 132kB/s]
+ 82%|########2 | 34.1M/41.5M [05:30<01:04, 120kB/s]
+ 82%|########2 | 34.1M/41.5M [05:30<00:55, 139kB/s]
+ 82%|########2 | 34.1M/41.5M [05:31<01:01, 125kB/s]
+ 82%|########2 | 34.2M/41.5M [05:31<00:53, 143kB/s]
+ 82%|########2 | 34.2M/41.5M [05:31<00:54, 142kB/s]
+ 82%|########2 | 34.2M/41.5M [05:31<01:00, 127kB/s]
+ 82%|########2 | 34.2M/41.5M [05:31<00:58, 130kB/s]
+ 83%|########2 | 34.2M/41.5M [05:31<00:59, 128kB/s]
+ 83%|########2 | 34.3M/41.5M [05:32<00:57, 131kB/s]
+ 83%|########2 | 34.3M/41.5M [05:32<00:56, 133kB/s]
+ 83%|########2 | 34.3M/41.5M [05:32<00:55, 135kB/s]
+ 83%|########2 | 34.3M/41.5M [05:32<01:12, 104kB/s]
+ 83%|########2 | 34.4M/41.5M [05:33<00:53, 139kB/s]
+ 83%|########2 | 34.4M/41.5M [05:33<00:58, 127kB/s]
+ 83%|########2 | 34.4M/41.5M [05:33<00:56, 130kB/s]
+ 83%|########3 | 34.4M/41.5M [05:33<00:54, 136kB/s]
+ 83%|########3 | 34.5M/41.5M [05:33<00:54, 136kB/s]
+ 83%|########3 | 34.5M/41.5M [05:33<00:55, 132kB/s]
+ 83%|########3 | 34.5M/41.5M [05:33<00:54, 134kB/s]
+ 83%|########3 | 34.5M/41.5M [05:34<00:49, 147kB/s]
+ 83%|########3 | 34.5M/41.5M [05:34<00:50, 144kB/s]
+ 83%|########3 | 34.6M/41.5M [05:34<00:51, 142kB/s]
+ 83%|########3 | 34.6M/41.5M [05:34<00:51, 141kB/s]
+ 83%|########3 | 34.6M/41.5M [05:34<00:51, 140kB/s]
+ 83%|########3 | 34.6M/41.5M [05:35<01:01, 117kB/s]
+ 83%|########3 | 34.6M/41.5M [05:35<01:05, 110kB/s]
+ 84%|########3 | 34.7M/41.5M [05:35<00:54, 132kB/s]
+ 84%|########3 | 34.7M/41.5M [05:35<00:55, 129kB/s]
+ 84%|########3 | 34.7M/41.5M [05:35<00:57, 123kB/s]
+ 84%|########3 | 34.7M/41.5M [05:36<01:12, 97.9kB/s]
+ 84%|########3 | 34.8M/41.5M [05:36<00:53, 131kB/s]
+ 84%|########3 | 34.8M/41.5M [05:36<00:58, 120kB/s]
+ 84%|########3 | 34.8M/41.5M [05:36<00:58, 121kB/s]
+ 84%|########3 | 34.8M/41.5M [05:36<01:22, 85.2kB/s]
+ 84%|########3 | 34.8M/41.5M [05:36<01:06, 105kB/s]
+ 84%|########3 | 34.8M/41.5M [05:37<01:17, 89.4kB/s]
+ 84%|########4 | 34.9M/41.5M [05:37<01:27, 79.4kB/s]
+ 84%|########4 | 34.9M/41.5M [05:37<01:33, 73.9kB/s]
+ 84%|########4 | 34.9M/41.5M [05:38<01:39, 69.6kB/s]
+ 84%|########4 | 34.9M/41.5M [05:38<01:47, 64.1kB/s]
+ 84%|########4 | 34.9M/41.5M [05:38<01:36, 71.1kB/s]
+ 84%|########4 | 34.9M/41.5M [05:38<01:29, 76.7kB/s]
+ 84%|########4 | 34.9M/41.5M [05:38<01:24, 81.0kB/s]
+ 84%|########4 | 35.0M/41.5M [05:38<01:21, 84.1kB/s]
+ 84%|########4 | 35.0M/41.5M [05:39<01:47, 63.5kB/s]
+ 84%|########4 | 35.0M/41.5M [05:39<01:31, 74.6kB/s]
+ 84%|########4 | 35.0M/41.5M [05:39<01:36, 70.5kB/s]
+ 84%|########4 | 35.0M/41.5M [05:39<01:24, 80.1kB/s]
+ 84%|########4 | 35.0M/41.5M [05:40<01:27, 77.6kB/s]
+ 84%|########4 | 35.1M/41.5M [05:40<01:33, 72.5kB/s]
+ 85%|########4 | 35.1M/41.5M [05:40<01:42, 65.8kB/s]
+ 85%|########4 | 35.1M/41.5M [05:40<01:38, 68.2kB/s]
+ 85%|########4 | 35.1M/41.5M [05:40<01:40, 66.9kB/s]
+ 85%|########4 | 35.1M/41.5M [05:41<01:30, 74.2kB/s]
+ 85%|########4 | 35.1M/41.5M [05:41<01:56, 57.2kB/s]
+ 85%|########4 | 35.1M/41.5M [05:41<01:31, 73.1kB/s]
+ 85%|########4 | 35.1M/41.5M [05:41<01:34, 70.0kB/s]
+ 85%|########4 | 35.2M/41.5M [05:41<01:27, 75.6kB/s]
+ 85%|########4 | 35.2M/41.5M [05:42<02:03, 53.7kB/s]
+ 85%|########4 | 35.2M/41.5M [05:42<01:21, 81.2kB/s]
+ 85%|########4 | 35.2M/41.5M [05:42<01:27, 75.4kB/s]
+ 85%|########4 | 35.2M/41.5M [05:43<01:43, 63.5kB/s]
+ 85%|########4 | 35.2M/41.5M [05:43<01:38, 66.3kB/s]
+ 85%|########4 | 35.3M/41.5M [05:43<01:37, 67.3kB/s]
+ 85%|########4 | 35.3M/41.5M [05:43<01:44, 62.3kB/s]
+ 85%|########5 | 35.3M/41.5M [05:43<01:42, 63.4kB/s]
+ 85%|########5 | 35.3M/41.5M [05:44<01:39, 65.5kB/s]
+ 85%|########5 | 35.3M/41.5M [05:44<01:29, 72.7kB/s]
+ 85%|########5 | 35.3M/41.5M [05:44<01:22, 78.1kB/s]
+ 85%|########5 | 35.3M/41.5M [05:44<01:24, 76.1kB/s]
+ 85%|########5 | 35.3M/41.5M [05:44<01:19, 81.1kB/s]
+ 85%|########5 | 35.4M/41.5M [05:44<01:16, 84.5kB/s]
+ 85%|########5 | 35.4M/41.5M [05:45<01:13, 86.9kB/s]
+ 85%|########5 | 35.4M/41.5M [05:45<01:12, 88.5kB/s]
+ 85%|########5 | 35.4M/41.5M [05:45<01:11, 89.7kB/s]
+ 85%|########5 | 35.4M/41.5M [05:45<01:05, 97.0kB/s]
+ 85%|########5 | 35.4M/41.5M [05:45<01:01, 103kB/s]
+ 85%|########5 | 35.5M/41.5M [05:46<01:17, 81.0kB/s]
+ 86%|########5 | 35.5M/41.5M [05:46<01:06, 94.6kB/s]
+ 86%|########5 | 35.5M/41.5M [05:46<01:06, 94.0kB/s]
+ 86%|########5 | 35.5M/41.5M [05:46<01:06, 93.6kB/s]
+ 86%|########5 | 35.5M/41.5M [05:46<01:05, 95.1kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:07, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:47<01:06, 92.3kB/s]
+ 86%|########5 | 35.6M/41.5M [05:48<01:06, 92.3kB/s]
+ 86%|########5 | 35.7M/41.5M [05:48<00:57, 106kB/s]
+ 86%|########6 | 35.7M/41.5M [05:48<00:59, 102kB/s]
+ 86%|########6 | 35.7M/41.5M [05:48<01:00, 101kB/s]
+ 86%|########6 | 35.7M/41.5M [05:48<00:54, 110kB/s]
+ 86%|########6 | 35.7M/41.5M [05:48<00:56, 107kB/s]
+ 86%|########6 | 35.8M/41.5M [05:49<00:52, 114kB/s]
+ 86%|########6 | 35.8M/41.5M [05:49<00:54, 110kB/s]
+ 86%|########6 | 35.8M/41.5M [05:49<00:50, 118kB/s]
+ 86%|########6 | 35.8M/41.5M [05:49<00:47, 124kB/s]
+ 86%|########6 | 35.9M/41.5M [05:49<00:46, 126kB/s]
+ 86%|########6 | 35.9M/41.5M [05:50<00:49, 118kB/s]
+ 87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
+ 87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
+ 87%|########6 | 35.9M/41.5M [05:50<00:42, 138kB/s]
+ 87%|########6 | 36.0M/41.5M [05:50<00:41, 138kB/s]
+ 87%|########6 | 36.0M/41.5M [05:50<00:37, 152kB/s]
+ 87%|########6 | 36.0M/41.5M [05:51<00:38, 148kB/s]
+ 87%|########6 | 36.0M/41.5M [05:51<00:51, 112kB/s]
+ 87%|########6 | 36.1M/41.5M [05:51<00:37, 153kB/s]
+ 87%|########7 | 36.1M/41.5M [05:52<00:47, 118kB/s]
+ 87%|########7 | 36.2M/41.5M [05:52<00:39, 141kB/s]
+ 87%|########7 | 36.2M/41.5M [05:52<00:43, 129kB/s]
+ 87%|########7 | 36.2M/41.5M [05:52<00:45, 122kB/s]
+ 87%|########7 | 36.2M/41.5M [05:52<00:48, 114kB/s]
+ 87%|########7 | 36.2M/41.5M [05:52<00:51, 108kB/s]
+ 87%|########7 | 36.2M/41.5M [05:53<00:47, 117kB/s]
+ 87%|########7 | 36.3M/41.5M [05:53<00:50, 110kB/s]
+ 87%|########7 | 36.3M/41.5M [05:53<00:46, 118kB/s]
+ 87%|########7 | 36.3M/41.5M [05:53<00:49, 110kB/s]
+ 88%|########7 | 36.3M/41.5M [05:53<00:45, 119kB/s]
+ 88%|########7 | 36.3M/41.5M [05:53<00:43, 125kB/s]
+ 88%|########7 | 36.4M/41.5M [05:54<00:41, 129kB/s]
+ 88%|########7 | 36.4M/41.5M [05:54<00:45, 118kB/s]
+ 88%|########7 | 36.4M/41.5M [05:54<00:42, 124kB/s]
+ 88%|########7 | 36.4M/41.5M [05:54<00:37, 142kB/s]
+ 88%|########7 | 36.5M/41.5M [05:54<00:37, 141kB/s]
+ 88%|########7 | 36.5M/41.5M [05:55<00:37, 140kB/s]
+ 88%|########7 | 36.5M/41.5M [05:55<00:37, 140kB/s]
+ 88%|########8 | 36.5M/41.5M [05:55<00:44, 118kB/s]
+ 88%|########8 | 36.6M/41.5M [05:55<00:32, 157kB/s]
+ 88%|########8 | 36.6M/41.5M [05:55<00:36, 141kB/s]
+ 88%|########8 | 36.6M/41.5M [05:56<00:36, 139kB/s]
+ 88%|########8 | 36.6M/41.5M [05:56<00:46, 109kB/s]
+ 88%|########8 | 36.7M/41.5M [05:56<00:35, 141kB/s]
+ 88%|########8 | 36.7M/41.5M [05:56<00:47, 106kB/s]
+ 89%|########8 | 36.7M/41.5M [05:56<00:40, 122kB/s]
+ 89%|########8 | 36.7M/41.5M [05:57<00:43, 114kB/s]
+ 89%|########8 | 36.8M/41.5M [05:57<00:45, 108kB/s]
+ 89%|########8 | 36.8M/41.5M [05:57<00:51, 96.7kB/s]
+ 89%|########8 | 36.8M/41.5M [05:57<01:02, 79.1kB/s]
+ 89%|########8 | 36.8M/41.5M [05:58<00:52, 93.7kB/s]
+ 89%|########8 | 36.8M/41.5M [05:58<00:59, 82.0kB/s]
+ 89%|########8 | 36.8M/41.5M [05:58<00:57, 84.2kB/s]
+ 89%|########8 | 36.9M/41.5M [05:58<01:10, 68.8kB/s]
+ 89%|########8 | 36.9M/41.5M [05:59<00:57, 84.3kB/s]
+ 89%|########8 | 36.9M/41.5M [05:59<00:56, 86.1kB/s]
+ 89%|########8 | 36.9M/41.5M [05:59<01:08, 69.8kB/s]
+ 89%|########9 | 36.9M/41.5M [05:59<01:01, 77.2kB/s]
+ 89%|########9 | 36.9M/41.5M [06:00<01:06, 71.9kB/s]
+ 89%|########9 | 37.0M/41.5M [06:00<01:28, 54.0kB/s]
+ 89%|########9 | 37.0M/41.5M [06:00<01:36, 49.2kB/s]
+ 89%|########9 | 37.0M/41.5M [06:01<01:27, 53.7kB/s]
+ 89%|########9 | 37.0M/41.5M [06:01<01:30, 52.3kB/s]
+ 89%|########9 | 37.0M/41.5M [06:01<01:32, 51.0kB/s]
+ 89%|########9 | 37.0M/41.5M [06:01<01:33, 49.9kB/s]
+ 89%|########9 | 37.0M/41.5M [06:01<01:35, 49.0kB/s]
+ 89%|########9 | 37.0M/41.5M [06:02<01:36, 48.3kB/s]
+ 89%|########9 | 37.0M/41.5M [06:02<01:17, 60.1kB/s]
+ 89%|########9 | 37.1M/41.5M [06:02<01:22, 56.2kB/s]
+ 89%|########9 | 37.1M/41.5M [06:02<01:26, 53.4kB/s]
+ 89%|########9 | 37.1M/41.5M [06:02<01:11, 64.6kB/s]
+ 89%|########9 | 37.1M/41.5M [06:03<01:17, 59.2kB/s]
+ 89%|########9 | 37.1M/41.5M [06:03<01:06, 68.9kB/s]
+ 89%|########9 | 37.1M/41.5M [06:03<01:00, 75.8kB/s]
+ 89%|########9 | 37.1M/41.5M [06:03<00:56, 80.7kB/s]
+ 90%|########9 | 37.1M/41.5M [06:03<00:54, 84.2kB/s]
+ 90%|########9 | 37.2M/41.5M [06:03<00:52, 86.6kB/s]
+ 90%|########9 | 37.2M/41.5M [06:04<00:51, 88.3kB/s]
+ 90%|########9 | 37.2M/41.5M [06:04<00:43, 103kB/s]
+ 90%|########9 | 37.2M/41.5M [06:04<00:34, 127kB/s]
+ 90%|########9 | 37.3M/41.5M [06:04<00:30, 145kB/s]
+ 90%|########9 | 37.3M/41.5M [06:04<00:28, 157kB/s]
+ 90%|########9 | 37.3M/41.5M [06:04<00:26, 165kB/s]
+ 90%|######### | 37.4M/41.5M [06:05<00:27, 157kB/s]
+ 90%|######### | 37.4M/41.5M [06:05<00:22, 193kB/s]
+ 90%|######### | 37.4M/41.5M [06:05<00:29, 146kB/s]
+ 90%|######### | 37.5M/41.5M [06:05<00:20, 201kB/s]
+ 90%|######### | 37.5M/41.5M [06:06<00:21, 197kB/s]
+ 90%|######### | 37.5M/41.5M [06:06<00:22, 181kB/s]
+ 91%|######### | 37.6M/41.5M [06:06<00:22, 182kB/s]
+ 91%|######### | 37.6M/41.5M [06:06<00:24, 170kB/s]
+ 91%|######### | 37.6M/41.5M [06:06<00:28, 141kB/s]
+ 91%|######### | 37.7M/41.5M [06:07<00:25, 155kB/s]
+ 91%|######### | 37.7M/41.5M [06:07<00:26, 151kB/s]
+ 91%|######### | 37.7M/41.5M [06:07<00:26, 148kB/s]
+ 91%|######### | 37.7M/41.5M [06:07<00:27, 145kB/s]
+ 91%|#########1| 37.8M/41.5M [06:07<00:24, 156kB/s]
+ 91%|#########1| 37.8M/41.5M [06:08<00:25, 151kB/s]
+ 91%|#########1| 37.8M/41.5M [06:08<00:28, 137kB/s]
+ 91%|#########1| 37.9M/41.5M [06:08<00:23, 162kB/s]
+ 91%|#########1| 37.9M/41.5M [06:08<00:24, 155kB/s]
+ 91%|#########1| 37.9M/41.5M [06:08<00:25, 150kB/s]
+ 91%|#########1| 37.9M/41.5M [06:08<00:25, 146kB/s]
+ 91%|#########1| 38.0M/41.5M [06:09<00:23, 158kB/s]
+ 92%|#########1| 38.0M/41.5M [06:09<00:24, 152kB/s]
+ 92%|#########1| 38.0M/41.5M [06:09<00:22, 162kB/s]
+ 92%|#########1| 38.0M/41.5M [06:09<00:26, 135kB/s]
+ 92%|#########1| 38.1M/41.5M [06:10<00:29, 123kB/s]
+ 92%|#########1| 38.1M/41.5M [06:10<00:24, 146kB/s]
+ 92%|#########1| 38.1M/41.5M [06:10<00:26, 133kB/s]
+ 92%|#########1| 38.1M/41.5M [06:10<00:28, 123kB/s]
+ 92%|#########2| 38.2M/41.5M [06:10<00:27, 127kB/s]
+ 92%|#########2| 38.2M/41.5M [06:11<00:29, 118kB/s]
+ 92%|#########2| 38.2M/41.5M [06:11<00:31, 110kB/s]
+ 92%|#########2| 38.2M/41.5M [06:11<00:28, 118kB/s]
+ 92%|#########2| 38.2M/41.5M [06:11<00:30, 111kB/s]
+ 92%|#########2| 38.3M/41.5M [06:11<00:28, 119kB/s]
+ 92%|#########2| 38.3M/41.5M [06:11<00:30, 111kB/s]
+ 92%|#########2| 38.3M/41.5M [06:12<00:31, 105kB/s]
+ 92%|#########2| 38.3M/41.5M [06:12<00:28, 115kB/s]
+ 92%|#########2| 38.3M/41.5M [06:12<00:30, 108kB/s]
+ 92%|#########2| 38.4M/41.5M [06:12<00:31, 104kB/s]
+ 92%|#########2| 38.4M/41.5M [06:12<00:28, 114kB/s]
+ 93%|#########2| 38.4M/41.5M [06:13<00:39, 82.7kB/s]
+ 93%|#########2| 38.4M/41.5M [06:13<00:26, 119kB/s]
+ 93%|#########2| 38.4M/41.5M [06:13<00:28, 112kB/s]
+ 93%|#########2| 38.5M/41.5M [06:13<00:28, 112kB/s]
+ 93%|#########2| 38.5M/41.5M [06:13<00:29, 107kB/s]
+ 93%|#########2| 38.5M/41.5M [06:14<00:27, 115kB/s]
+ 93%|#########2| 38.5M/41.5M [06:14<00:26, 117kB/s]
+ 93%|#########2| 38.5M/41.5M [06:14<00:26, 115kB/s]
+ 93%|#########2| 38.6M/41.5M [06:14<00:25, 122kB/s]
+ 93%|#########3| 38.6M/41.5M [06:14<00:25, 118kB/s]
+ 93%|#########3| 38.6M/41.5M [06:15<00:24, 124kB/s]
+ 93%|#########3| 38.6M/41.5M [06:15<00:23, 128kB/s]
+ 93%|#########3| 38.7M/41.5M [06:15<00:23, 127kB/s]
+ 93%|#########3| 38.7M/41.5M [06:15<00:22, 130kB/s]
+ 93%|#########3| 38.7M/41.5M [06:15<00:22, 133kB/s]
+ 93%|#########3| 38.7M/41.5M [06:15<00:21, 134kB/s]
+ 93%|#########3| 38.8M/41.5M [06:15<00:19, 147kB/s]
+ 93%|#########3| 38.8M/41.5M [06:16<00:19, 144kB/s]
+ 94%|#########3| 38.8M/41.5M [06:16<00:18, 155kB/s]
+ 94%|#########3| 38.8M/41.5M [06:16<00:24, 115kB/s]
+ 94%|#########3| 38.9M/41.5M [06:16<00:18, 148kB/s]
+ 94%|#########3| 38.9M/41.5M [06:16<00:19, 142kB/s]
+ 94%|#########3| 38.9M/41.5M [06:17<00:26, 104kB/s]
+ 94%|#########3| 38.9M/41.5M [06:17<00:19, 137kB/s]
+ 94%|#########3| 38.9M/41.5M [06:17<00:21, 125kB/s]
+ 94%|#########3| 39.0M/41.5M [06:17<00:21, 124kB/s]
+ 94%|#########3| 39.0M/41.5M [06:17<00:21, 124kB/s]
+ 94%|#########3| 39.0M/41.5M [06:17<00:21, 123kB/s]
+ 94%|#########3| 39.0M/41.5M [06:18<00:21, 124kB/s]
+ 94%|#########4| 39.0M/41.5M [06:18<00:22, 113kB/s]
+ 94%|#########4| 39.0M/41.5M [06:18<00:22, 115kB/s]
+ 94%|#########4| 39.1M/41.5M [06:18<00:20, 123kB/s]
+ 94%|#########4| 39.1M/41.5M [06:18<00:20, 123kB/s]
+ 94%|#########4| 39.1M/41.5M [06:18<00:25, 97.0kB/s]
+ 94%|#########4| 39.1M/41.5M [06:19<00:20, 123kB/s]
+ 94%|#########4| 39.1M/41.5M [06:19<00:26, 92.5kB/s]
+ 94%|#########4| 39.2M/41.5M [06:19<00:24, 98.6kB/s]
+ 94%|#########4| 39.2M/41.5M [06:19<00:25, 97.0kB/s]
+ 94%|#########4| 39.2M/41.5M [06:20<00:25, 95.7kB/s]
+ 94%|#########4| 39.2M/41.5M [06:20<00:25, 94.8kB/s]
+ 95%|#########4| 39.2M/41.5M [06:20<00:25, 94.0kB/s]
+ 95%|#########4| 39.2M/41.5M [06:20<00:25, 93.5kB/s]
+ 95%|#########4| 39.2M/41.5M [06:20<00:25, 93.2kB/s]
+ 95%|#########4| 39.3M/41.5M [06:20<00:25, 92.9kB/s]
+ 95%|#########4| 39.3M/41.5M [06:21<00:24, 92.7kB/s]
+ 95%|#########4| 39.3M/41.5M [06:21<00:24, 92.6kB/s]
+ 95%|#########4| 39.3M/41.5M [06:21<00:21, 106kB/s]
+ 95%|#########4| 39.3M/41.5M [06:21<00:22, 102kB/s]
+ 95%|#########4| 39.4M/41.5M [06:21<00:19, 113kB/s]
+ 95%|#########4| 39.4M/41.5M [06:21<00:18, 121kB/s]
+ 95%|#########4| 39.4M/41.5M [06:22<00:19, 112kB/s]
+ 95%|#########5| 39.4M/41.5M [06:22<00:18, 120kB/s]
+ 95%|#########5| 39.4M/41.5M [06:22<00:17, 125kB/s]
+ 95%|#########5| 39.5M/41.5M [06:22<00:16, 129kB/s]
+ 95%|#########5| 39.5M/41.5M [06:22<00:15, 132kB/s]
+ 95%|#########5| 39.5M/41.5M [06:23<00:13, 148kB/s]
+ 95%|#########5| 39.5M/41.5M [06:23<00:14, 145kB/s]
+ 95%|#########5| 39.6M/41.5M [06:23<00:14, 143kB/s]
+ 95%|#########5| 39.6M/41.5M [06:23<00:14, 142kB/s]
+ 95%|#########5| 39.6M/41.5M [06:23<00:16, 122kB/s]
+ 96%|#########5| 39.7M/41.5M [06:24<00:12, 152kB/s]
+ 96%|#########5| 39.7M/41.5M [06:24<00:13, 146kB/s]
+ 96%|#########5| 39.7M/41.5M [06:24<00:13, 144kB/s]
+ 96%|#########5| 39.7M/41.5M [06:24<00:12, 153kB/s]
+ 96%|#########5| 39.7M/41.5M [06:24<00:12, 148kB/s]
+ 96%|#########5| 39.8M/41.5M [06:24<00:12, 145kB/s]
+ 96%|#########5| 39.8M/41.5M [06:25<00:11, 157kB/s]
+ 96%|#########5| 39.8M/41.5M [06:25<00:11, 152kB/s]
+ 96%|#########6| 39.9M/41.5M [06:25<00:10, 161kB/s]
+ 96%|#########6| 39.9M/41.5M [06:25<00:10, 155kB/s]
+ 96%|#########6| 39.9M/41.5M [06:25<00:10, 164kB/s]
+ 96%|#########6| 39.9M/41.5M [06:25<00:10, 159kB/s]
+ 96%|#########6| 40.0M/41.5M [06:26<00:09, 164kB/s]
+ 96%|#########6| 40.0M/41.5M [06:26<00:09, 159kB/s]
+ 96%|#########6| 40.0M/41.5M [06:26<00:09, 164kB/s]
+ 97%|#########6| 40.0M/41.5M [06:26<00:08, 170kB/s]
+ 97%|#########6| 40.1M/41.5M [06:26<00:08, 175kB/s]
+ 97%|#########6| 40.1M/41.5M [06:27<00:10, 142kB/s]
+ 97%|#########6| 40.1M/41.5M [06:27<00:08, 164kB/s]
+ 97%|#########6| 40.2M/41.5M [06:27<00:08, 157kB/s]
+ 97%|#########6| 40.2M/41.5M [06:27<00:09, 151kB/s]
+ 97%|#########6| 40.2M/41.5M [06:27<00:08, 151kB/s]
+ 97%|#########6| 40.2M/41.5M [06:27<00:08, 158kB/s]
+ 97%|#########7| 40.3M/41.5M [06:28<00:07, 166kB/s]
+ 97%|#########7| 40.3M/41.5M [06:28<00:07, 171kB/s]
+ 97%|#########7| 40.3M/41.5M [06:28<00:06, 175kB/s]
+ 97%|#########7| 40.4M/41.5M [06:28<00:06, 178kB/s]
+ 97%|#########7| 40.4M/41.5M [06:28<00:06, 182kB/s]
+ 97%|#########7| 40.4M/41.5M [06:28<00:06, 183kB/s]
+ 97%|#########7| 40.4M/41.5M [06:29<00:08, 131kB/s]
+ 98%|#########7| 40.5M/41.5M [06:29<00:05, 178kB/s]
+ 98%|#########7| 40.5M/41.5M [06:29<00:06, 167kB/s]
+ 98%|#########7| 40.5M/41.5M [06:29<00:06, 159kB/s]
+ 98%|#########7| 40.6M/41.5M [06:29<00:05, 166kB/s]
+ 98%|#########7| 40.6M/41.5M [06:30<00:05, 158kB/s]
+ 98%|#########7| 40.6M/41.5M [06:30<00:05, 166kB/s]
+ 98%|#########7| 40.7M/41.5M [06:30<00:05, 171kB/s]
+ 98%|#########8| 40.7M/41.5M [06:30<00:05, 162kB/s]
+ 98%|#########8| 40.7M/41.5M [06:30<00:04, 183kB/s]
+ 98%|#########8| 40.8M/41.5M [06:31<00:04, 169kB/s]
+ 98%|#########8| 40.8M/41.5M [06:31<00:04, 173kB/s]
+ 98%|#########8| 40.8M/41.5M [06:31<00:04, 178kB/s]
+ 98%|#########8| 40.8M/41.5M [06:31<00:04, 142kB/s]
+ 98%|#########8| 40.9M/41.5M [06:31<00:03, 167kB/s]
+ 99%|#########8| 40.9M/41.5M [06:32<00:03, 159kB/s]
+ 99%|#########8| 40.9M/41.5M [06:32<00:04, 125kB/s]
+ 99%|#########8| 41.0M/41.5M [06:32<00:03, 152kB/s]
+ 99%|#########8| 41.0M/41.5M [06:32<00:03, 139kB/s]
+ 99%|#########8| 41.0M/41.5M [06:32<00:03, 139kB/s]
+ 99%|#########8| 41.0M/41.5M [06:33<00:03, 139kB/s]
+ 99%|#########8| 41.0M/41.5M [06:33<00:03, 139kB/s]
+ 99%|#########8| 41.1M/41.5M [06:33<00:03, 135kB/s]
+ 99%|#########9| 41.1M/41.5M [06:33<00:03, 136kB/s]
+ 99%|#########9| 41.1M/41.5M [06:33<00:02, 137kB/s]
+ 99%|#########9| 41.1M/41.5M [06:33<00:03, 115kB/s]
+ 99%|#########9| 41.1M/41.5M [06:34<00:03, 108kB/s]
+ 99%|#########9| 41.2M/41.5M [06:34<00:03, 111kB/s]
+ 99%|#########9| 41.2M/41.5M [06:34<00:02, 112kB/s]
+ 99%|#########9| 41.2M/41.5M [06:34<00:03, 82.0kB/s]
+ 99%|#########9| 41.2M/41.5M [06:35<00:02, 95.8kB/s]
+ 99%|#########9| 41.2M/41.5M [06:35<00:03, 75.4kB/s]
+ 99%|#########9| 41.2M/41.5M [06:35<00:03, 79.2kB/s]
+ 99%|#########9| 41.3M/41.5M [06:35<00:02, 82.4kB/s]
+ 99%|#########9| 41.3M/41.5M [06:35<00:02, 85.0kB/s]
+100%|#########9| 41.3M/41.5M [06:36<00:02, 86.9kB/s]
+100%|#########9| 41.3M/41.5M [06:36<00:02, 88.4kB/s]
+100%|#########9| 41.3M/41.5M [06:36<00:01, 89.5kB/s]
+100%|#########9| 41.3M/41.5M [06:36<00:01, 84.5kB/s]
+100%|#########9| 41.4M/41.5M [06:36<00:01, 86.7kB/s]
+100%|#########9| 41.4M/41.5M [06:37<00:01, 72.5kB/s]
+100%|#########9| 41.4M/41.5M [06:37<00:01, 89.0kB/s]
+100%|#########9| 41.4M/41.5M [06:37<00:01, 71.1kB/s]
+100%|#########9| 41.4M/41.5M [06:37<00:00, 75.9kB/s]
+100%|#########9| 41.4M/41.5M [06:38<00:00, 75.4kB/s]
+100%|#########9| 41.5M/41.5M [06:38<00:00, 72.5kB/s]
+100%|#########9| 41.5M/41.5M [06:38<00:00, 65.2kB/s]
+100%|#########9| 41.5M/41.5M [06:38<00:00, 53.9kB/s]
+100%|##########| 41.5M/41.5M [06:38<00:00, 109kB/s]
</pre></div>
</div>
</div>
@@ -587,6 +2535,7 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
OneFlow top-1 id: 281, class name: tabby, tabby cat
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 5.320 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-oneflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/f7ae979fbe61064749ce0fb7a621eb4c/from_oneflow.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_oneflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 6e397ef35..0ec25558d 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 9.167 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.320 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 253f76ef3..e8bbc55a5 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -387,9 +387,9 @@ 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]
- 46%|####5 | 20.5M/44.7M [00:00<00:00, 215MB/s]
- 92%|#########1| 41.0M/44.7M [00:00<00:00, 213MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 218MB/s]
+ 36%|###6 | 16.1M/44.7M [00:00<00:00, 167MB/s]
+ 73%|#######3 | 32.7M/44.7M [00:00<00:00, 171MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 175MB/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 295127083..c35fbe807 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,6 +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 8.649 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index d19df62bc..8af71ecfc 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -300,18 +300,18 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:38.395</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>12:07.759</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:09.167</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>00:59.567</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:57.172</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:39.056</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:32.705</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
-<li><p><strong>00:22.488</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:21.973</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
-<li><p><strong>00:19.785</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:14.124</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
-<li><p><strong>00:02.358</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
+<li><p><strong>07:05.320</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
+<li><p><strong>01:08.649</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
+<li><p><strong>01:08.320</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>00:58.707</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
+<li><p><strong>00:24.614</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:23.848</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:21.673</strong>: <a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></li>
+<li><p><strong>00:19.501</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:14.176</strong>: <a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></li>
+<li><p><strong>00:02.951</strong>: <a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index bee442bff..4fef51556 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -627,7 +627,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.9353 15.9319 16.3844 15.7128 0.1878
+ 16.0599 15.9668 16.4660 15.8947 0.1898
</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 a4cf24d6f..bb06cb1c0 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -409,16 +409,52 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 2%|2 | 3.48M/170M [00:00<00:04, 36.5MB/s]
- 4%|4 | 6.97M/170M [00:00<00:05, 33.7MB/s]
- 18%|#7 | 30.1M/170M [00:00<00:01, 125MB/s]
- 29%|##8 | 49.0M/170M [00:00<00:00, 153MB/s]
- 43%|####2 | 72.3M/170M [00:00<00:00, 186MB/s]
- 56%|#####5 | 95.0M/170M [00:00<00:00, 203MB/s]
- 69%|######8 | 117M/170M [00:00<00:00, 210MB/s]
- 82%|########1 | 139M/170M [00:00<00:00, 217MB/s]
- 94%|#########3| 159M/170M [00:00<00:00, 189MB/s]
-100%|##########| 170M/170M [00:01<00:00, 177MB/s]
+ 2%|1 | 2.56M/170M [00:00<00:06, 26.5MB/s]
+ 4%|4 | 7.06M/170M [00:00<00:04, 38.3MB/s]
+ 7%|7 | 12.3M/170M [00:00<00:03, 45.6MB/s]
+ 10%|9 | 16.7M/170M [00:00<00:03, 40.5MB/s]
+ 12%|#2 | 21.0M/170M [00:00<00:03, 41.9MB/s]
+ 15%|#4 | 25.2M/170M [00:00<00:03, 42.5MB/s]
+ 17%|#7 | 29.3M/170M [00:00<00:04, 34.8MB/s]
+ 19%|#9 | 32.8M/170M [00:00<00:04, 30.9MB/s]
+ 21%|##1 | 35.9M/170M [00:01<00:05, 27.6MB/s]
+ 23%|##2 | 38.7M/170M [00:01<00:05, 26.0MB/s]
+ 24%|##4 | 41.4M/170M [00:01<00:05, 26.3MB/s]
+ 26%|##5 | 44.0M/170M [00:01<00:05, 26.1MB/s]
+ 27%|##7 | 46.5M/170M [00:01<00:04, 26.0MB/s]
+ 29%|##8 | 49.0M/170M [00:01<00:05, 24.2MB/s]
+ 30%|### | 51.4M/170M [00:01<00:05, 24.0MB/s]
+ 32%|###1 | 53.7M/170M [00:01<00:05, 22.8MB/s]
+ 33%|###2 | 55.9M/170M [00:02<00:05, 22.0MB/s]
+ 34%|###4 | 58.0M/170M [00:02<00:05, 22.0MB/s]
+ 35%|###5 | 60.2M/170M [00:02<00:05, 22.2MB/s]
+ 37%|###6 | 62.6M/170M [00:02<00:04, 23.0MB/s]
+ 38%|###8 | 64.9M/170M [00:02<00:04, 23.4MB/s]
+ 40%|###9 | 67.2M/170M [00:02<00:05, 19.3MB/s]
+ 41%|#### | 69.4M/170M [00:02<00:05, 20.2MB/s]
+ 43%|####2 | 72.4M/170M [00:02<00:04, 21.3MB/s]
+ 45%|####5 | 76.8M/170M [00:02<00:03, 27.6MB/s]
+ 48%|####8 | 82.0M/170M [00:03<00:02, 34.9MB/s]
+ 51%|##### | 86.2M/170M [00:03<00:02, 37.2MB/s]
+ 53%|#####3 | 90.4M/170M [00:03<00:02, 39.0MB/s]
+ 56%|#####6 | 95.9M/170M [00:03<00:01, 44.5MB/s]
+ 59%|#####9 | 100M/170M [00:03<00:01, 42.4MB/s]
+ 61%|######1 | 104M/170M [00:03<00:01, 38.8MB/s]
+ 64%|######3 | 108M/170M [00:03<00:01, 33.4MB/s]
+ 66%|######6 | 112M/170M [00:03<00:01, 35.6MB/s]
+ 69%|######8 | 117M/170M [00:03<00:01, 39.8MB/s]
+ 71%|#######1 | 121M/170M [00:04<00:01, 35.2MB/s]
+ 73%|#######3 | 125M/170M [00:04<00:01, 34.0MB/s]
+ 75%|#######5 | 128M/170M [00:04<00:01, 29.1MB/s]
+ 78%|#######7 | 132M/170M [00:04<00:01, 31.1MB/s]
+ 81%|######## | 137M/170M [00:04<00:00, 38.2MB/s]
+ 84%|########4 | 143M/170M [00:04<00:00, 44.2MB/s]
+ 87%|########6 | 148M/170M [00:04<00:00, 40.2MB/s]
+ 89%|########9 | 152M/170M [00:04<00:00, 40.1MB/s]
+ 93%|#########2| 158M/170M [00:05<00:00, 45.7MB/s]
+ 96%|#########5| 162M/170M [00:05<00:00, 47.0MB/s]
+ 98%|#########8| 167M/170M [00:05<00:00, 43.3MB/s]
+100%|##########| 170M/170M [00:05<00:00, 32.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -516,7 +552,7 @@ 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 56.410 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 4.324 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index 19758d366..a5491b9c8 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -450,7 +450,11 @@ training. Other models require a full post training calibration.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
0%| | 0.00/13.6M [00:00<?, ?B/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 204MB/s]
+ 22%|##2 | 3.01M/13.6M [00:00<00:00, 31.4MB/s]
+ 45%|####4 | 6.06M/13.6M [00:00<00:00, 31.5MB/s]
+ 67%|######6 | 9.08M/13.6M [00:00<00:00, 28.6MB/s]
+ 88%|########8 | 11.9M/13.6M [00:00<00:00, 28.3MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 30.3MB/s]
</pre></div>
</div>
</div>
@@ -544,7 +548,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3360 90.2477 91.4267 90.0722 0.2370
+ 90.4285 90.3099 98.7001 90.1933 0.8536
</pre></div>
</div>
<div class="admonition note">
@@ -583,7 +587,7 @@ 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 6.030 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.743 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index cf8a54bc2..3d493d218 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -545,7 +545,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.3097 120.1003 129.1709 119.4653 1.2372
+ 120.8243 120.7925 122.3121 120.2380 0.3238
</pre></div>
</div>
<div class="admonition note">
@@ -573,7 +573,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 56.792 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 58.258 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 21d3bea8c..4011286e1 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -482,7 +482,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 11.226 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 15.223 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 6db4fdb7a..84c0c95ce 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,22 +415,24 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 2%|1 | 2586/132723 [00:00<00:05, 25858.05KB/s]
- 9%|8 | 11362/132723 [00:00<00:01, 62266.11KB/s]
- 15%|#5 | 20231/132723 [00:00<00:01, 74327.37KB/s]
- 22%|##1 | 29129/132723 [00:00<00:01, 80106.91KB/s]
- 29%|##8 | 38051/132723 [00:00<00:01, 83389.85KB/s]
- 35%|###5 | 46969/132723 [00:00<00:01, 85350.78KB/s]
- 42%|####2 | 55905/132723 [00:00<00:00, 86656.50KB/s]
- 49%|####8 | 64910/132723 [00:00<00:00, 87733.14KB/s]
- 56%|#####5 | 73833/132723 [00:00<00:00, 88198.17KB/s]
- 62%|######2 | 82770/132723 [00:01<00:00, 88558.56KB/s]
- 69%|######9 | 91714/132723 [00:01<00:00, 88824.64KB/s]
- 76%|#######5 | 100775/132723 [00:01<00:00, 89365.73KB/s]
- 83%|########2 | 109793/132723 [00:01<00:00, 89606.85KB/s]
- 90%|########9 | 118843/132723 [00:01<00:00, 89874.94KB/s]
- 96%|#########6| 127892/132723 [00:01<00:00, 90057.50KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 85317.78KB/s]
+ 2%|1 | 2292/132723 [00:00<00:05, 22039.86KB/s]
+ 5%|5 | 7205/132723 [00:00<00:03, 37708.46KB/s]
+ 11%|#1 | 15069/132723 [00:00<00:02, 56226.20KB/s]
+ 17%|#7 | 22575/132723 [00:00<00:01, 63618.75KB/s]
+ 23%|##2 | 30293/132723 [00:00<00:01, 68484.68KB/s]
+ 29%|##8 | 37929/132723 [00:00<00:01, 71152.24KB/s]
+ 35%|###4 | 45813/132723 [00:00<00:01, 73659.68KB/s]
+ 41%|#### | 53785/132723 [00:00<00:01, 75585.61KB/s]
+ 47%|####6 | 61819/132723 [00:00<00:00, 77069.65KB/s]
+ 52%|#####2 | 69541/132723 [00:01<00:00, 77107.72KB/s]
+ 58%|#####8 | 77560/132723 [00:01<00:00, 78047.74KB/s]
+ 64%|######4 | 85513/132723 [00:01<00:00, 78494.83KB/s]
+ 70%|####### | 93364/132723 [00:01<00:00, 77056.50KB/s]
+ 76%|#######6 | 101471/132723 [00:01<00:00, 78251.92KB/s]
+ 83%|########2 | 109543/132723 [00:01<00:00, 78986.93KB/s]
+ 88%|########8 | 117447/132723 [00:01<00:00, 78901.84KB/s]
+ 95%|#########4| 125545/132723 [00:01<00:00, 79520.71KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 73670.89KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -475,7 +477,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
</pre></div>
</div>
<img alt="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" />
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 17.943 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 20.148 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 0b15ffe42..54d12bd09 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:19.186</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:37.507</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:56.410</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
-<li><p><strong>02:17.943</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
-<li><p><strong>01:56.792</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
-<li><p><strong>01:11.226</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
-<li><p><strong>01:06.030</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
-<li><p><strong>00:28.090</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
-<li><p><strong>00:22.494</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
-<li><p><strong>00:00.201</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
+<li><p><strong>03:04.324</strong>: <a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></li>
+<li><p><strong>02:20.148</strong>: <a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></li>
+<li><p><strong>01:58.258</strong>: <a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></li>
+<li><p><strong>01:15.223</strong>: <a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></li>
+<li><p><strong>01:07.743</strong>: <a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></li>
+<li><p><strong>00:29.021</strong>: <a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></li>
+<li><p><strong>00:22.584</strong>: <a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></li>
+<li><p><strong>00:00.205</strong>: <a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index abab67e60..beee9d5b0 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -590,7 +590,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip75eed920-edf7-4b76-ad95-e9b3dd4ee65e 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.zipbacdc21b-e9b5-4639-bedc-d265e0bfc80a 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 45a017d27..c9b16db04 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -300,12 +300,12 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.861</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.518</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:36.153</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
-<li><p><strong>00:02.382</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
-<li><p><strong>00:01.119</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
-<li><p><strong>00:00.208</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:36.779</strong>: <a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></li>
+<li><p><strong>00:02.405</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
+<li><p><strong>00:01.118</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.216</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index f7e8d411b..625bc8e7a 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -486,10 +486,10 @@ profile the execution time of each passes.</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6679us [6679us] (45.95%; 45.95%)
-FoldScaleAxis: 7856us [7us] (54.05%; 54.05%)
- FoldConstant: 7849us [1582us] (54.00%; 99.92%)
- InferType: 6268us [6268us] (43.12%; 79.85%)
+InferType: 6481us [6481us] (45.44%; 45.44%)
+FoldScaleAxis: 7781us [6us] (54.56%; 54.56%)
+ FoldConstant: 7775us [1596us] (54.52%; 99.92%)
+ InferType: 6179us [6179us] (43.33%; 79.47%)
</pre></div>
</div>
</div>
@@ -512,10 +512,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6375us [6375us] (44.82%; 44.82%)
-FoldScaleAxis: 7848us [5us] (55.18%; 55.18%)
- FoldConstant: 7843us [1636us] (55.14%; 99.94%)
- InferType: 6207us [6207us] (43.64%; 79.15%)
+InferType: 6237us [6237us] (44.69%; 44.69%)
+FoldScaleAxis: 7720us [5us] (55.31%; 55.31%)
+ FoldConstant: 7715us [1619us] (55.28%; 99.93%)
+ InferType: 6095us [6095us] (43.68%; 79.01%)
</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 2305749da..d3e3b8bb7 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -534,7 +534,7 @@ latency of convolution.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 34.746341 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.227840 ms
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 3b454e5eb..d292409b0 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.828640 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.558863 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 9af5ca694..679d8da33 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -431,8 +431,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018536
-Baseline: 3.203548
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018951
+Baseline: 3.301327
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -494,7 +494,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.298506
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.314647
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -563,7 +563,7 @@ vastly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.335232
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.343285
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -626,7 +626,7 @@ the access pattern for A matrix is more cache friendly.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117339
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.117855
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -711,7 +711,7 @@ flattening.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110376
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110636
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -799,7 +799,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111631
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111104
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -891,7 +891,7 @@ write to C when all the block results are ready.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145255
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144939
</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 b3c029c2e..63b85fe9e 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.481</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.993</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:31.760</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
-<li><p><strong>00:01.493</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
-<li><p><strong>00:01.228</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
+<li><p><strong>00:32.370</strong>: <a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></li>
+<li><p><strong>00:01.393</strong>: <a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></li>
+<li><p><strong>00:01.231</strong>: <a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index b7482adae..b5adb6ecd 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:10.990</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:16.692</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:33.018</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>01:20.023</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:43.110</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
-<li><p><strong>00:17.617</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
-<li><p><strong>00:08.685</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
-<li><p><strong>00:08.539</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
+<li><p><strong>02:35.612</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
+<li><p><strong>01:21.080</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:43.239</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:19.013</strong>: <a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></li>
+<li><p><strong>00:09.008</strong>: <a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></li>
+<li><p><strong>00:08.740</strong>: <a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index 009c203c5..bc251fbb2 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
@@ -470,611 +470,88 @@ 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" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
allocate(pad_temp.shared: Pointer(shared float32), float32, [648]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [1152]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [14], [], scope="local", align=32)[0] = 0f32
- conv2d_nchw_1[1] = 0f32
+ allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [4], [], scope="local", align=8)[0] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[1] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[12] = 0f32
- conv2d_nchw_1[13] = 0f32
for (rc.outer.outer: int32, 0, 64) {
let cse_var_2: int32 = (rc.outer.outer*392)
let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((9 <= threadIdx.x_1) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[(((cse_var_2 + (floordiv(threadIdx.x_1, 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 56)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 56), 81)) && (floormod((threadIdx.x_1 + 56), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 56), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 56), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 112)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 112), 81)) && (floormod((threadIdx.x_1 + 31), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 112), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 112), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 168)] = @tir.if_then_else((((9 <= floormod((threadIdx.x_1 + 168), 81)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 168), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 168), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 224)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 224), 81)) && (floormod((threadIdx.x_1 + 62), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 224), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 224), 81), 9)*7)) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 280)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 280), 81)) && (floormod((threadIdx.x_1 + 37), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 280), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 280), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 336)] = @tir.if_then_else(((1 <= floormod((threadIdx.x_1 + 3), 9)) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 336), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 336), 81), 9)*7)) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 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 + 392), 81), 9)*7)) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 448)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 448), 81)) && (floormod((threadIdx.x_1 + 43), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 448), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 448), 81), 9)*7)) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 504)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 18), 81) < 72) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 504), 81)*49)) + (floormod((floordiv(threadIdx.x_1, 9) + 2), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- pad_temp.shared_1[(threadIdx.x_1 + 560)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 560), 81)) && (floormod((threadIdx.x_1 + 74), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 560), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 560), 81), 9)*7)) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56;
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 616)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 49), 81) < 72) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 616), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 616), 81), 9)*7)) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[(threadIdx.x_2*6)] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6))]
- kernel.shared_1[((threadIdx.x_2*6) + 1)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 2)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 3)]
- kernel.shared_1[((threadIdx.x_2*6) + 4)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 4)]
- kernel.shared_1[((threadIdx.x_2*6) + 5)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 12)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 5)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1[((threadIdx.x_2*6) + 336)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 337)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 338)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 16), 24)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 339)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 340)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 341)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 14), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 17), 24)*3)) + 2)]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [648], [], 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" = 196;
+ 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" = 196;
+ 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" = 196;
+ if @tir.likely((threadIdx.x_1 < 60), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else((((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_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- kernel.shared_1[((threadIdx.x_2*6) + 672)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 673)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 674)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 8), 24)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*6) + 675)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3))]
- kernel.shared_1[((threadIdx.x_2*6) + 676)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*6) + 677)] = kernel[(((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 9), 24)*3)) + 2)]
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 52), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 7), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 104), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 14), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 156), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 1), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 208), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 28), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 260), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 35), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 312), 72), 9)*9)) + (floormod((floordiv(threadIdx.x_2, 3) + 2), 3)*3)) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 364), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 49), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 416), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 56), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[(((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 18)*4608)) + cse_var_1) + (floormod((floordiv(threadIdx.x_2, 9) + 4), 8)*9)) + floormod(threadIdx.x_2, 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 520), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 70), 9), 3)*3)) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
+ if @tir.likely((threadIdx.x_2 < 148), dtype=bool) {
+ kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 18)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 572), 72), 9)*9)) + (floordiv(floormod((threadIdx.x_2 + 77), 9), 3)*3)) + floormod((threadIdx.x_2 + 2), 3))]
}
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 56 {
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1008)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64512)]
+ for (rc.outer.inner: int32, 0, 4) {
+ for (ry.outer.inner: int32, 0, 3) {
+ for (rx.outer.inner: int32, 0, 3) {
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1152)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1728)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1161)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1737)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 648)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1224)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1800)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 657)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1233)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((((((rc.outer.inner*162) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + (ry.outer.inner*9)) + rx.outer.inner) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*144) + (rc.outer.inner*18)) + (ry.outer.inner*3)) + rx.outer.inner) + 1809)]))
+ }
}
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1009)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64513)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1010)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(threadIdx.x_2, 12)*6)) + 64514)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1011)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64512)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1012)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64513)]
- }
- if @tir.likely((threadIdx.x_2 < 24), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*6) + 1013)] = kernel[(((((blockIdx.x*73728) + (floordiv(floordiv(threadIdx.x_2, 4), 3)*4608)) + cse_var_1) + (floormod(((threadIdx.x_2*2) + 1), 24)*3)) + 64514)]
- }
- }
- for (rc.outer.inner: int32, 0, 2) {
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36))]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 3)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 6)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 9)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 12)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 15)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 18)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 21)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 24)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 27)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 30)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 33)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[((rc.outer.inner*324) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 72)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 75)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 27)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 36)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 45)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 54)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 63)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 72)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 78)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 81)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 84)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 108)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 117)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 126)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 135)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 144)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 153)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 87)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 90)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 93)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 189)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 198)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 207)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 216)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 225)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 234)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 96)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 99)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 102)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 270)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 279)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 288)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 297)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 306)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 315)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 105)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 1)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 4)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 7)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 10)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 13)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 16)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 19)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 22)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 25)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 28)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 31)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 34)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 73)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 76)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 28)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 37)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 46)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 55)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 64)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 73)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 79)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 82)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 85)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 109)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 118)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 127)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 136)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 145)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 154)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 88)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 91)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 94)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 190)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 199)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 208)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 217)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 226)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 235)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 97)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 100)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 103)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 271)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 280)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 289)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 298)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 307)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 316)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 106)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 2)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 5)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 8)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 11)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 14)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 17)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 20)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 23)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 26)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 29)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 32)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 35)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 74)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 77)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 29)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 38)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 47)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 56)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 65)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 74)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 80)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 83)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 86)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 110)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 119)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 128)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 137)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 146)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 155)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 89)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 92)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 95)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 191)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 200)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 209)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 218)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 227)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 236)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 98)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 101)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 104)]))
- conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 272)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 281)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 290)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 299)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 308)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
- conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[(((rc.outer.inner*324) + floormod(threadIdx.x, 7)) + 317)]*kernel.shared_1[(((floordiv(threadIdx.x, 7)*144) + (rc.outer.inner*36)) + 107)]))
}
}
}
for (i1.inner: int32, 0, 2) {
- for (i2.inner: int32, 0, 7) {
- compute[(((((blockIdx.x*784) + (floordiv(threadIdx.x, 7)*98)) + (i1.inner*49)) + (i2.inner*7)) + floormod(threadIdx.x, 7))] = max((conv2d_nchw_1[((i1.inner*7) + i2.inner)] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 7)*2)) + i1.inner)]), 0f32)
- }
+ compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 392)] = max((conv2d_nchw_1[(i1.inner + 2)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 8)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 784)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 16)]), 0f32)
+ compute[(((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49)) + 1176)] = max((conv2d_nchw_1[(i1.inner + 6)] + bias[((((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*2)) + i1.inner) + 24)]), 0f32)
}
}
}
@@ -1112,7 +589,7 @@ cooperative fetching, unrolling and operator fusion.</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.209 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.311 ms
</pre></div>
</div>
</div>
@@ -1144,20 +621,20 @@ conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=8)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
+conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=4)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=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=4)
-conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
@@ -1165,10 +642,10 @@ compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=2)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=8)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=4)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
@@ -1189,16 +666,16 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
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=6)
+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=56)
+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=196)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=56)
+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=196)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -1216,588 +693,69 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(56) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[14];
+extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[8];
__shared__ float pad_temp_shared[648];
- __shared__ float kernel_shared[1152];
+ __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[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[1] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = ((((9 <= ((int)threadIdx.x)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 56)] = (((((9 <= ((((int)threadIdx.x) + 56) % 81)) && (((((int)threadIdx.x) + 56) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 56) / 81) * 49)) + ((((((int)threadIdx.x) + 56) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 112)] = (((((9 <= ((((int)threadIdx.x) + 31) % 81)) && (((((int)threadIdx.x) + 31) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 112) / 81) * 49)) + ((((((int)threadIdx.x) + 31) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 168)] = ((((9 <= ((((int)threadIdx.x) + 6) % 81)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 168) / 81) * 49)) + ((((((int)threadIdx.x) + 6) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 224)] = (((((9 <= ((((int)threadIdx.x) + 62) % 81)) && (((((int)threadIdx.x) + 62) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 224) / 81) * 49)) + ((((((int)threadIdx.x) + 62) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 280)] = (((((9 <= ((((int)threadIdx.x) + 37) % 81)) && (((((int)threadIdx.x) + 37) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 280) / 81) * 49)) + ((((((int)threadIdx.x) + 37) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 336)] = (((1 <= ((((int)threadIdx.x) + 3) % 9)) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 336) / 81) * 49)) + ((((((int)threadIdx.x) + 12) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
+ 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 * 392) + ((((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) + 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 * 392) + (((((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) + 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 * 392) + (((((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) + 448)] = (((((9 <= ((((int)threadIdx.x) + 43) % 81)) && (((((int)threadIdx.x) + 43) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 448) / 81) * 49)) + ((((((int)threadIdx.x) + 43) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 504)] = ((((((int)threadIdx.x) < 54) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 504) / 81) * 49)) + (((((int)threadIdx.x) / 9) + 2) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 560)] = (((((9 <= ((((int)threadIdx.x) + 74) % 81)) && (((((int)threadIdx.x) + 74) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 560) / 81) * 49)) + ((((((int)threadIdx.x) + 74) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[(((int)threadIdx.x) + 616)] = ((((((int)threadIdx.x) < 23) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 616) / 81) * 49)) + ((((((int)threadIdx.x) + 49) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 6)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6))];
- kernel_shared[((((int)threadIdx.x) * 6) + 1)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 2)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 3)];
- kernel_shared[((((int)threadIdx.x) * 6) + 4)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 4)];
- kernel_shared[((((int)threadIdx.x) * 6) + 5)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 5)];
- kernel_shared[((((int)threadIdx.x) * 6) + 336)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 337)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 338)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 16) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 339)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 340)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 341)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 56) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 17) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 672)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 673)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 674)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 8) % 24) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 6) + 675)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3))];
- kernel_shared[((((int)threadIdx.x) * 6) + 676)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 6) + 677)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 112) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) * 2) + 9) % 24) * 3)) + 2)];
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1008)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64512)];
+ if (((int)threadIdx.x) < 60) {
+ pad_temp_shared[(((int)threadIdx.x) + 588)] = ((((((int)threadIdx.x) < 51) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 588) / 81) * 49)) + ((((((int)threadIdx.x) + 21) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
}
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1009)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64513)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1010)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64514)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1011)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64515)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1012)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64516)];
- }
- if (((int)threadIdx.x) < 24) {
- kernel_shared[((((int)threadIdx.x) * 6) + 1013)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 12) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) % 12) * 6)) + 64517)];
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 52) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 12) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 1) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 44) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 8) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((((int)threadIdx.x) / 3) + 2) % 3) * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 4) % 72) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[(((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) / 9) + 4) & 7) * 9)) + (((int)threadIdx.x) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 7) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ if (((int)threadIdx.x) < 148) {
+ kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 68) % 72) / 9) * 9)) + ((((((int)threadIdx.x) + 5) % 9) / 3) * 3)) + ((((int)threadIdx.x) + 2) % 3))];
}
__syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[(((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36))]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 3)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 6)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 9)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 12)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 15)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 18)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 21)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 24)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 27)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 30)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 33)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((rc_outer_inner * 324) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 72)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 75)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 27)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 36)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 45)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 54)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 63)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 72)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 78)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 81)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 84)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 108)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 117)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 126)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 135)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 144)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 153)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 87)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 90)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 93)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 189)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 198)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 207)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 216)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 225)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 234)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 96)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 99)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 102)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 270)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 279)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 288)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 297)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 306)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 315)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 105)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 1)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 4)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 7)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 10)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 13)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 16)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 19)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 22)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 25)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 28)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 31)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 34)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 73)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 76)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 28)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 37)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 46)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 55)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 64)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 73)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 79)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 82)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 85)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 109)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 118)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 127)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 136)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 145)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 154)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 88)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 91)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 94)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 190)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 199)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 208)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 217)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 226)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 235)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 97)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 100)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 103)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 271)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 280)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 289)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 298)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 307)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 316)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 106)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 2)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 5)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 8)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 11)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 14)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 17)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 20)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 23)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 26)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 29)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 32)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 35)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 74)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 77)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 29)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 38)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 47)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 56)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 65)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 74)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 80)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 83)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 86)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 110)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 119)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 128)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 137)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 146)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 155)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 89)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 92)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 95)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 191)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 200)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 209)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 218)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 227)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 236)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 98)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 101)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 104)]));
- conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 272)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 281)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 290)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 299)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 308)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
- conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[(((rc_outer_inner * 324) + (((int)threadIdx.x) % 7)) + 317)] * kernel_shared[((((((int)threadIdx.x) / 7) * 144) + (rc_outer_inner * 36)) + 107)]));
+ for (int rc_outer_inner = 0; rc_outer_inner < 4; ++rc_outer_inner) {
+ for (int ry_outer_inner = 0; ry_outer_inner < 3; ++ry_outer_inner) {
+ for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1152)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1728)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1161)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1737)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 648)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1224)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[(((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1800)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 657)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1233)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[((((((rc_outer_inner * 162) + (((((int)threadIdx.x) % 49) / 7) * 9)) + (ry_outer_inner * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[((((((((int)threadIdx.x) / 49) * 144) + (rc_outer_inner * 18)) + (ry_outer_inner * 3)) + rx_outer_inner) + 1809)]));
+ }
+ }
}
}
for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
- compute[(((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 7) * 98)) + (i1_inner * 49)) + (i2_inner * 7)) + (((int)threadIdx.x) % 7))] = max((conv2d_nchw[((i1_inner * 7) + i2_inner)] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 7) * 2)) + i1_inner)]), 0.000000e+00f);
- }
+ compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 392)] = max((conv2d_nchw[(i1_inner + 2)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 8)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 784)] = max((conv2d_nchw[(i1_inner + 4)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 16)]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49)) + 1176)] = max((conv2d_nchw[(i1_inner + 6)] + bias[((((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner) + 24)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1835,7 +793,7 @@ 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 33.018 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.612 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index f095b5e53..f26feabd3 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -878,7 +878,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 10.7175 10.7332 10.7417 10.6776 0.0284
+ 9.9292 9.9303 9.9840 9.8732 0.0452
</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 4ad078dbc..8454a8e95 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -897,7 +897,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 751.5126 750.9964 753.1246 750.4167 1.1642
+ 759.2062 759.2453 759.2652 759.1082 0.0698
</pre></div>
</div>
</div>
@@ -919,7 +919,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 20.023 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.080 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index db3aabe8a..84d5bf14f 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,78 +600,32 @@ 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_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_9: placeholder_17: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_18: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), placeholder_5: placeholder_16: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
for (i0.outer.i1.outer.fused: int32, 0, 16) "parallel" {
allocate(compute_4: Pointer(global float32), float32, [4096]), storage_scope = global {
- for (i.outer.inner: int32, 0, 16) {
+ for (i.outer.inner: int32, 0, 32) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 8) {
- let cse_var_1: int32 = (((i.outer.inner*256) + (i.inner.init*32)) + (nb_j.inner*16))
- {
- compute_5: Buffer(compute_4, float32, [4096], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ for (i.inner.init: int32, 0, 4) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [4096], [])[((((i.outer.inner*128) + (i.inner.init*32)) + (nb_j.inner*16)) + j.init)] = 0f32
}
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 8) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
- let cse_var_19: int32 = ((i.outer.inner*2048) + (i.inner*256))
- let cse_var_18: int32 = (((i.outer.inner*256) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_17: int32 = (cse_var_18 + 9)
- let cse_var_16: int32 = (cse_var_18 + 8)
- let cse_var_15: int32 = (cse_var_18 + 7)
- 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 (elem_idx: int32, 0, let cse_var_1: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 4) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i0.outer.i1.outer.fused*2) + nb_j.inner)
+ let cse_var_2: int32 = ((((i.outer.inner*128) + (i.inner*32)) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i.outer.inner*1024) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
}
for (i0.inner: int32, 0, 128) {
- let cse_var_22: int32 = ((i0.inner*512) + (i0.outer.i1.outer.fused*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((i0.inner*512) + (i0.outer.i1.outer.fused*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -710,7 +664,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.840 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.450 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 966aae3b7..5a78de907 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:43.830</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.237</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:42.919</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.235</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
-<li><p><strong>00:00.231</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
-<li><p><strong>00:00.228</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
-<li><p><strong>00:00.217</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
+<li><p><strong>00:43.320</strong>: <a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.240</strong>: <a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></li>
+<li><p><strong>00:00.227</strong>: <a class="reference internal" href="tune_relay_mobile_gpu.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-mobile-gpu-py"><span class="std std-ref">Auto-tuning a Convolutional Network for Mobile GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_mobile_gpu.py</span></code>)</p></li>
+<li><p><strong>00:00.226</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.224</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index c86f67406..1acb0d463 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1142,8 +1142,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 103.02/103.02 result: MeasureResult(costs=(0.0022470772291666666,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6823019981384277, timestamp=1654823162.7531817) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 6 GFLOPS: 67.40/67.40 result: MeasureResult(costs=(0.0034348572,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.5976083278656006, timestamp=1654825918.712542) [('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: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1266,7 +1266,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1389,7 +1389,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1512,7 +1512,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1530,7 +1530,7 @@ No: 10 GFLOPS: 0.00/103.02 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: 0.00/103.02 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1653,7 +1653,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1776,7 +1776,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -1899,7 +1899,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2022,7 +2022,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2145,7 +2145,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2268,7 +2268,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2391,7 +2391,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 571, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 523, in _build_func_common
@@ -2514,7 +2514,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 854, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/103.02 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/67.40 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 721, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 685, in run_through_rpc
@@ -2602,7 +2602,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007fab4438ffa2
+ 12: 0x00007f3c09a09fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 133.54/133.54 result: MeasureResult(costs=(0.0017335372258064517,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1547482013702393, timestamp=1654823188.942235) [('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: 144.22/144.22 result: MeasureResult(costs=(0.00160517407,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4326956272125244, timestamp=1654825945.0753632) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2706,7 +2706,7 @@ and measure running time.</p>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
-Time cost of this operator: 0.002110
+Time cost of this operator: 0.002067
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index bc6f5116e..9ec6a52f9 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -556,10 +556,10 @@ 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 314.1 98.772 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.0 0.943 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.905 0.285 (1, 1, 10, 10, 3) 1 1
-Total_time - 318.005 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 313.9 98.719 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.172 0.998 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.902 0.284 (1, 1, 10, 10, 3) 1 1
+Total_time - 317.974 - - - -
</pre></div>
</div>
</div>
@@ -611,10 +611,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 91.7 97.154 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.74 1.843 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.947 1.003 (1, 1, 10, 10, 3) 1 1
-Total_time - 94.386 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 321.9 99.055 (1, 3, 10, 10, 2) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 2.183 0.672 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.889 0.274 (1, 3, 10, 10, 1) 1 1
+Total_time - 324.972 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 9fd421fef..f28f691ee 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -552,8 +552,8 @@ objects to other stuff? We can display some examples from our datasets using <co
</div>
<img alt="../../_images/sphx_glr_micro_train_001.png" class="sphx-glr-single-img" src="../../_images/sphx_glr_micro_train_001.png" />
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp2tj1xuz5/images/target contains 8144 images
-/tmp/tmp2tj1xuz5/images/random contains 5000 images
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpbnc8mgfi/images/target contains 8144 images
+/tmp/tmpbnc8mgfi/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -666,11 +666,11 @@ the time on our validation set).</p>
</div>
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 54s - loss: 0.2194 - accuracy: 0.9243 - val_loss: 0.1387 - val_accuracy: 0.9539
+328/328 - 54s - loss: 0.2162 - accuracy: 0.9268 - val_loss: 0.1468 - val_accuracy: 0.9581
Epoch 2/3
-328/328 - 52s - loss: 0.0982 - accuracy: 0.9638 - val_loss: 0.1187 - val_accuracy: 0.9611
+328/328 - 52s - loss: 0.0937 - accuracy: 0.9649 - val_loss: 0.1316 - val_accuracy: 0.9573
Epoch 3/3
-328/328 - 52s - loss: 0.0646 - accuracy: 0.9751 - val_loss: 0.1186 - val_accuracy: 0.9607
+328/328 - 52s - loss: 0.0678 - accuracy: 0.9746 - val_loss: 0.1096 - val_accuracy: 0.9622
</pre></div>
</div>
</div>
@@ -959,7 +959,7 @@ 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 55.643 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 12.281 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download 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 9e28b8b81..1d6e916f2 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:42.129</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>04:58.551</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>04:55.643</strong>: <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></li>
-<li><p><strong>00:42.149</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
-<li><p><strong>00:03.719</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
-<li><p><strong>00:00.206</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>04:12.281</strong>: <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></li>
+<li><p><strong>00:41.955</strong>: <a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></li>
+<li><p><strong>00:03.688</strong>: <a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></li>
+<li><p><strong>00:00.214</strong>: <a class="reference internal" href="micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py"><span class="std std-ref">Executing a Tiny Model with TVMC Micro</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tvmc.py</span></code>)</p></li>
+<li><p><strong>00:00.206</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
<li><p><strong>00:00.206</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
-<li><p><strong>00:00.205</strong>: <a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_relay/sg_execution_times.html b/docs/how_to/work_with_relay/sg_execution_times.html
index 63525fb44..9c6af24fe 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:11.746</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.749</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:09.907</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
-<li><p><strong>00:01.617</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
-<li><p><strong>00:00.222</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
+<li><p><strong>00:10.033</strong>: <a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></li>
+<li><p><strong>00:01.491</strong>: <a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></li>
+<li><p><strong>00:00.225</strong>: <a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index a181149d3..2ebbf9255 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -300,16 +300,16 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:05.749</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.613</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.101</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
-<li><p><strong>00:01.160</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
-<li><p><strong>00:00.743</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
-<li><p><strong>00:00.717</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
-<li><p><strong>00:00.317</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
-<li><p><strong>00:00.253</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
-<li><p><strong>00:00.229</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
-<li><p><strong>00:00.228</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
+<li><p><strong>00:02.011</strong>: <a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></li>
+<li><p><strong>00:01.132</strong>: <a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></li>
+<li><p><strong>00:00.717</strong>: <a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></li>
+<li><p><strong>00:00.706</strong>: <a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></li>
+<li><p><strong>00:00.318</strong>: <a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></li>
+<li><p><strong>00:00.251</strong>: <a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></li>
+<li><p><strong>00:00.247</strong>: <a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></li>
+<li><p><strong>00:00.231</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index 52a87b94b..e0eb29b74 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/tmprceh4wqg/input0.cc'\nsource_filename = \"/tmp/tmprceh4wqg/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/tmppvfr2ekq/input0.cc'\nsource_filename = \"/tmp/tmppvfr2ekq/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 55abf50d4..8682e82d6 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1715,7 +1715,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1752,7 +1752,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 74c227a4d..9779d91b8 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/fc8fdae61/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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 04e742763..ebf382c5b 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/fc8fdae61/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/fe299d768/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/fc8fdae61/web/src/memory.ts#L363">memory.ts:363</a></li>
... 2624 lines suppressed ...