You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/05/20 01:12:03 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@5e29dddd02193a440c18a1d98fef9023cb008788)
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 0ef3d1cb3 deploying docs (apache/tvm@5e29dddd02193a440c18a1d98fef9023cb008788)
0ef3d1cb3 is described below
commit 0ef3d1cb3c191b867632362e359fda8ed10cabee
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri May 20 01:11:57 2022 +0000
deploying docs (apache/tvm@5e29dddd02193a440c18a1d98fef9023cb008788)
---
.../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 | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 18 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 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 | 1961 +++++++++++++-------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 84 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 12 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 12 +-
.../work_with_relay/sg_execution_times.rst.txt | 8 +-
.../work_with_schedules/sg_execution_times.rst.txt | 18 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 6 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 56 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 26 +-
.../tutorial/tensor_expr_get_started.rst.txt | 49 +-
docs/commit_hash | 2 +-
docs/genindex.html | 4 +
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 759 +++++++-
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 | 2 +-
docs/how_to/compile_models/sg_execution_times.html | 22 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 30 +-
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 | 37 +-
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 | 1961 +++++++++++++-------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 84 +-
.../tune_with_autotvm/sg_execution_times.html | 12 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 12 +-
.../how_to/work_with_relay/sg_execution_times.html | 8 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/objects.inv | Bin 22377 -> 22389 bytes
docs/reference/api/python/auto_scheduler.html | 4 +-
docs/reference/api/python/autotvm.html | 22 +
.../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 | 5 +-
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 +-
118 files changed, 4197 insertions(+), 2252 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 80d9afec3..3648f6aba 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.zip69bf84d8-fe7f-42be-9dc6-2d49679d54ab from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip9bbde507-bb5f-467a-81f5-ff1cb26580ad 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 bf46845a4..dd10ae077 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<07:43, 93.9kB/s]
0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
0%| | 96.0k/41.5M [00:00<03:28, 209kB/s]
0%| | 160k/41.5M [00:00<02:38, 274kB/s]
1%| | 296k/41.5M [00:00<01:33, 461kB/s]
1%|1 | 608k/41.5M [00:01<00:46, 923kB/s]
3%|2 | 1.08M/41.5M [00:01<00:27, 1.57MB/s]
5%|5 | 2.10M/41.5M [00:01<00:13, 3.01MB/s]
9%|8 | 3.61M/41.5M [00:01<00:08, 4.89MB/s]
12%|#2 | 5.11M/41.5M [00:01<00:06, 6.14MB/s]
16%|#5 | 6.62M/41.5M [00:01<00:05, 7.02MB/s]
20%|#9 | 8.12M/41.5M [00:02<00:04, 7.62MB/s]
23%|##3 | 9.62M/41.5M [00:02<00:04, 8.01MB/s]
27%|##6 | 11.1M/41.5M [00:02<00:03, 8.31MB/s]
30%|### | 12.6M/41.5M [00:02<00:03, 8.49MB/s]
34%|###4 | 14.1M/41.5M [00:02<00:03, 8.65MB/s]
38%|###7 | 15.6M/41.5M [00:02<00
:03, 8.74MB/s]
41%|####1 | 17.1M/41.5M [00:03<00:02, 8.82MB/s]
45%|####4 | 18.6M/41.5M [00:03<00:02, 8.85MB/s]
49%|####8 | 20.1M/41.5M [00:03<00:02, 8.89MB/s]
52%|#####2 | 21.6M/41.5M [00:03<00:02, 8.87MB/s]
56%|#####5 | 23.1M/41.5M [00:03<00:02, 8.91MB/s]
59%|#####9 | 24.6M/41.5M [00:04<00:01, 8.93MB/s]
63%|######2 | 26.1M/41.5M [00:04<00:01, 8.95MB/s]
67%|######6 | 27.6M/41.5M [00:04<00:01, 10.0MB/s]
70%|####### | 29.1M/41.5M [00:04<00:01, 10.5MB/s]
73%|#######2 | 30.1M/41.5M [00:04<00:01, 10.1MB/s]
75%|#######4 | 31.1M/41.5M [00:04<00:01, 8.74MB/s]
77%|#######7 | 32.1M/41.5M [00:04<00:01, 8.28MB/s]
81%|######## | 33.6M/41.5M [00:05<00:00, 9.24MB/s]
83%|########3 | 34.5M/41.5M [00:05<00:01, 6.91MB/s]
85%|########4 | 35.2M/41.5M [00:05<00:01, 6.21MB/s]
88%|########8 | 36.7M/41.5M [00:05<00:00, 6.96MB/s]
92%|#########2| 38.2M/41.5M [00:05<00:00, 7.57MB/s]
96%|####
#####5| 39.7M/41.5M [00:05<00:00, 8.01MB/s]
99%|#########9| 41.2M/41.5M [00:06<00:00, 8.29MB/s]
100%|##########| 41.5M/41.5M [00:06<00:00, 7.07MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<22:35, 32.1kB/s]
0%| | 32.0k/41.5M [00:00<15:57, 45.4kB/s]
0%| | 48.0k/41.5M [00:01<13:50, 52.4kB/s]
0%| | 56.0k/41.5M [00:01<21:34, 33.6kB/s]
0%| | 64.0k/41.5M [00:01<21:51, 33.1kB/s]
0%| | 80.0k/41.5M [00:02<17:21, 41.7kB/s]
0%| | 96.0k/41.5M [00:02<19:19, 37.4kB/s]
0%| | 104k/41.5M [00:03<24:49, 29.1kB/s]
0%| | 112k/41.5M [00:03<29:34, 24.5kB/s]
0%| | 128k/41.5M [00:04<32:03, 22.6kB/s]
0%| | 136k/41.5M [00:05<50:05, 14.4kB/s]
0%| | 144k/41.5M [00:07<1:25:02, 8.50kB/s]
0%| | 152k/41.5M [00:08<1:20:35, 8.97kB/s]
0%| | 160k/41.5M [00:09<1:17:06, 9.37kB/s]
0%| | 168k/41.5M [00:09<1:08:13, 10.6kB/s]
0%| | 176k/41.5M [00:10<55:17, 13.1kB/s]
0%| | 184k/41.5M [0
0:13<1:51:54, 6.45kB/s]
0%| | 192k/41.5M [00:14<1:44:10, 6.93kB/s]
0%| | 200k/41.5M [00:14<1:21:31, 8.85kB/s]
0%| | 208k/41.5M [00:15<1:22:40, 8.73kB/s]
1%| | 216k/41.5M [00:15<1:11:29, 10.1kB/s]
1%| | 224k/41.5M [00:16<1:03:36, 11.3kB/s]
1%| | 232k/41.5M [00:17<1:11:31, 10.1kB/s]
1%| | 240k/41.5M [00:17<56:51, 12.7kB/s]
1%| | 248k/41.5M [00:18<53:17, 13.5kB/s]
1%| | 256k/41.5M [00:20<1:35:07, 7.58kB/s]
1%| | 264k/41.5M [00:20<1:13:21, 9.82kB/s]
1%| | 272k/41.5M [00:20<58:06, 12.4kB/s]
1%| | 280k/41.5M [00:21<47:26, 15.2kB/s]
1%| | 288k/41.5M [00:21<51:59, 13.8kB/s]
1%| | 304k/41.5M [00:22<44:37, 16.1kB/s]
1%| | 320k/41.5M [00:22<31:22, 22.9kB/s]
1%| | 328k/41.5M [00:23<29:25, 24.5kB/s]
1%| | 336k/41.5M [00:23<37:21, 19.3kB/s]
1%| | 344k/41.5M [00:24<34:47, 20.7kB/s]
1%| | 352k/41.5M [00:24<42:26, 16.9kB/s]
1%| | 360k/41.5M [00:25<43:05, 16.7kB/s]
1%| | 368k/41.5M [00:25<37:34, 19.1kB/s]
1%| | 376k/41.5M [00:26<35:57, 20.0kB/s]
1%| | 384k/41.5M [00:26<30:08, 23.8kB/s]
1%| | 392k/41.5M [00:26<30:40, 23.4kB/s]
1%| | 400k/41.5M [00:26<26:19, 27.3kB/s]
1%| | 408k/41.5M [00:26<23:14, 30.9kB/s]
1%| | 416k/41.5M [00:27<21:05, 34.1kB/s]
1%|1 | 432k/41.5M [00:27<15:03, 47.6kB/s]
1%|1 | 440k/41.5M [00:27<15:16, 47.0kB/s]
1%|1 | 448k/41.5M [00:27<15:27, 46.4kB/s]
1%|1 | 464k/41.5M [00:27<12:15, 58.5kB/s]
1%|1 | 472k/41.5M [00:28<13:07, 54.6kB/s]
1%|1 | 480k/41.5M [00:28<13:49, 51.8kB/s]
1%|1 | 496k/41.5M [00:28<11:22, 63.0kB/s]
1%|1 | 512k/41.5M [00:28<10:06,
70.9kB/s]
1%|1 | 520k/41.5M [00:28<11:19, 63.2kB/s]
1%|1 | 536k/41.5M [00:28<10:03, 71.1kB/s]
1%|1 | 552k/41.5M [00:29<09:19, 76.7kB/s]
1%|1 | 568k/41.5M [00:29<08:52, 80.6kB/s]
1%|1 | 584k/41.5M [00:29<08:34, 83.4kB/s]
1%|1 | 600k/41.5M [00:29<08:23, 85.2kB/s]
1%|1 | 624k/41.5M [00:29<07:08, 100kB/s]
2%|1 | 640k/41.5M [00:30<07:21, 97.0kB/s]
2%|1 | 664k/41.5M [00:30<06:35, 108kB/s]
2%|1 | 696k/41.5M [00:30<05:29, 130kB/s]
2%|1 | 728k/41.5M [00:30<04:55, 145kB/s]
2%|1 | 760k/41.5M [00:30<04:35, 155kB/s]
2%|1 | 800k/41.5M [00:30<04:02, 176kB/s]
2%|1 | 840k/41.5M [00:31<03:43, 191kB/s]
2%|2 | 888k/41.5M [00:31<03:18, 214kB/s]
2%|2 | 944k/41.5M [00:31<02:54, 244kB/s]
2%|2 | 0.98M/41.5M [00:31<02:45, 256kB/s]
3%|2 | 1.04M/41.5M [00:31<02
:44, 258kB/s]
3%|2 | 1.11M/41.5M [00:32<02:37, 268kB/s]
3%|2 | 1.14M/41.5M [00:32<05:16, 134kB/s]
3%|3 | 1.27M/41.5M [00:34<05:54, 119kB/s]
3%|3 | 1.39M/41.5M [00:34<04:06, 171kB/s]
3%|3 | 1.42M/41.5M [00:34<04:16, 164kB/s]
3%|3 | 1.45M/41.5M [00:35<04:39, 150kB/s]
4%|3 | 1.48M/41.5M [00:35<05:51, 120kB/s]
4%|3 | 1.50M/41.5M [00:36<08:34, 81.5kB/s]
4%|3 | 1.54M/41.5M [00:36<07:20, 95.0kB/s]
4%|3 | 1.55M/41.5M [00:36<08:12, 85.1kB/s]
4%|3 | 1.57M/41.5M [00:38<17:24, 40.1kB/s]
4%|3 | 1.59M/41.5M [00:40<32:07, 21.7kB/s]
4%|3 | 1.59M/41.5M [00:41<33:30, 20.8kB/s]
4%|3 | 1.60M/41.5M [00:42<52:56, 13.2kB/s]
4%|3 | 1.61M/41.5M [00:43<51:16, 13.6kB/s]
4%|3 | 1.62M/41.5M [00:43<45:22, 15.4kB/s]
4%|3 | 1.62M/41.5M [00:43<40:07, 17.4kB/s]
4%|3 |
1.63M/41.5M [00:44<35:41, 19.5kB/s]
4%|3 | 1.64M/41.5M [00:44<32:07, 21.7kB/s]
4%|3 | 1.66M/41.5M [00:44<23:09, 30.1kB/s]
4%|4 | 1.66M/41.5M [00:45<32:52, 21.2kB/s]
4%|4 | 1.68M/41.5M [00:46<37:05, 18.8kB/s]
4%|4 | 1.70M/41.5M [00:48<46:25, 15.0kB/s]
4%|4 | 1.70M/41.5M [00:49<59:12, 11.7kB/s]
4%|4 | 1.71M/41.5M [00:50<1:05:27, 10.6kB/s]
4%|4 | 1.72M/41.5M [00:50<54:42, 12.7kB/s]
4%|4 | 1.73M/41.5M [00:51<51:45, 13.4kB/s]
4%|4 | 1.73M/41.5M [00:51<43:37, 15.9kB/s]
4%|4 | 1.74M/41.5M [00:51<37:30, 18.5kB/s]
4%|4 | 1.75M/41.5M [00:53<1:02:31, 11.1kB/s]
4%|4 | 1.77M/41.5M [00:53<45:13, 15.4kB/s]
4%|4 | 1.77M/41.5M [00:54<47:44, 14.5kB/s]
4%|4 | 1.78M/41.5M [00:55<53:21, 13.0kB/s]
4%|4 | 1.80M/41.5M [00:55<39:54, 17.4kB/s]
4%|4 | 1.80M/41.5M [00:56<4
0:41, 17.0kB/s]
4%|4 | 1.81M/41.5M [00:56<35:55, 19.3kB/s]
4%|4 | 1.82M/41.5M [00:56<37:49, 18.3kB/s]
4%|4 | 1.83M/41.5M [00:57<39:16, 17.6kB/s]
4%|4 | 1.84M/41.5M [00:57<40:23, 17.2kB/s]
4%|4 | 1.84M/41.5M [00:58<35:02, 19.8kB/s]
4%|4 | 1.85M/41.5M [00:59<49:56, 13.9kB/s]
5%|4 | 1.87M/41.5M [01:01<1:13:07, 9.47kB/s]
5%|4 | 1.88M/41.5M [01:02<1:14:05, 9.34kB/s]
5%|4 | 1.88M/41.5M [01:02<1:02:51, 11.0kB/s]
5%|4 | 1.89M/41.5M [01:03<50:02, 13.8kB/s]
5%|4 | 1.90M/41.5M [01:03<44:40, 15.5kB/s]
5%|4 | 1.91M/41.5M [01:03<36:20, 19.0kB/s]
5%|4 | 1.91M/41.5M [01:03<30:16, 22.8kB/s]
5%|4 | 1.92M/41.5M [01:03<25:55, 26.7kB/s]
5%|4 | 1.93M/41.5M [01:04<22:49, 30.3kB/s]
5%|4 | 1.94M/41.5M [01:04<20:37, 33.5kB/s]
5%|4 | 1.95M/41.5M [01:04<19:04, 36.2kB/s]
5%|4 | 1.95M/41.5M [01:04<17:58, 38.5kB/s]
5%|4 | 1.96M/41.5M [01:04<17:11, 40.2kB/s]
5%|4 | 1.98M/41.5M [01:05<12:48, 53.9kB/s]
5%|4 | 1.98M/41.5M [01:05<13:26, 51.4kB/s]
5%|4 | 2.00M/41.5M [01:05<11:03, 62.4kB/s]
5%|4 | 2.01M/41.5M [01:05<12:02, 57.3kB/s]
5%|4 | 2.02M/41.5M [01:05<10:20, 66.7kB/s]
5%|4 | 2.05M/41.5M [01:05<07:56, 86.8kB/s]
5%|4 | 2.07M/41.5M [01:06<06:49, 101kB/s]
5%|5 | 2.09M/41.5M [01:06<06:11, 111kB/s]
5%|5 | 2.12M/41.5M [01:06<05:49, 118kB/s]
5%|5 | 2.16M/41.5M [01:06<04:35, 150kB/s]
5%|5 | 2.19M/41.5M [01:06<04:19, 159kB/s]
5%|5 | 2.23M/41.5M [01:07<03:34, 192kB/s]
5%|5 | 2.28M/41.5M [01:07<03:10, 215kB/s]
6%|5 | 2.34M/41.5M [01:07<02:47, 245kB/s]
6%|5 | 2.39M/41.5M [01:07<02:34, 266kB/s]
6%|5 | 2.46M/41.5M [01:07<
02:19, 294kB/s]
6%|6 | 2.53M/41.5M [01:08<02:19, 293kB/s]
6%|6 | 2.62M/41.5M [01:08<02:54, 234kB/s]
6%|6 | 2.65M/41.5M [01:09<04:11, 162kB/s]
7%|6 | 2.74M/41.5M [01:09<03:10, 213kB/s]
7%|6 | 2.83M/41.5M [01:09<02:43, 247kB/s]
7%|6 | 2.87M/41.5M [01:09<02:59, 226kB/s]
7%|6 | 2.90M/41.5M [01:10<03:24, 198kB/s]
7%|7 | 2.93M/41.5M [01:10<03:45, 179kB/s]
7%|7 | 2.95M/41.5M [01:10<05:35, 120kB/s]
7%|7 | 2.98M/41.5M [01:11<05:30, 122kB/s]
7%|7 | 3.00M/41.5M [01:11<06:15, 108kB/s]
7%|7 | 3.02M/41.5M [01:11<07:56, 84.7kB/s]
7%|7 | 3.04M/41.5M [01:12<10:40, 62.9kB/s]
7%|7 | 3.06M/41.5M [01:12<09:36, 69.9kB/s]
7%|7 | 3.08M/41.5M [01:12<09:50, 68.2kB/s]
7%|7 | 3.09M/41.5M [01:13<11:15, 59.6kB/s]
7%|7 | 3.10M/41.5M [01:13<13:56, 48.1kB/s]
7%|7 | 3.
11M/41.5M [01:13<15:05, 44.4kB/s]
8%|7 | 3.12M/41.5M [01:14<16:57, 39.5kB/s]
8%|7 | 3.14M/41.5M [01:15<18:13, 36.8kB/s]
8%|7 | 3.15M/41.5M [01:15<18:42, 35.8kB/s]
8%|7 | 3.16M/41.5M [01:15<19:09, 35.0kB/s]
8%|7 | 3.16M/41.5M [01:15<19:34, 34.2kB/s]
8%|7 | 3.17M/41.5M [01:16<19:53, 33.7kB/s]
8%|7 | 3.18M/41.5M [01:16<20:08, 33.2kB/s]
8%|7 | 3.19M/41.5M [01:16<20:20, 32.9kB/s]
8%|7 | 3.20M/41.5M [01:16<20:29, 32.7kB/s]
8%|7 | 3.20M/41.5M [01:17<20:35, 32.5kB/s]
8%|7 | 3.21M/41.5M [01:17<20:40, 32.4kB/s]
8%|7 | 3.22M/41.5M [01:18<39:06, 17.1kB/s]
8%|7 | 3.23M/41.5M [01:18<30:48, 21.7kB/s]
8%|7 | 3.24M/41.5M [01:19<33:30, 20.0kB/s]
8%|7 | 3.26M/41.5M [01:19<23:59, 27.9kB/s]
8%|7 | 3.27M/41.5M [01:19<23:17, 28.7kB/s]
8%|7 | 3.27M/41.5M [01:20<27:47, 24.0
kB/s]
8%|7 | 3.28M/41.5M [01:20<31:23, 21.3kB/s]
8%|7 | 3.29M/41.5M [01:21<28:31, 23.4kB/s]
8%|7 | 3.30M/41.5M [01:22<43:49, 15.2kB/s]
8%|7 | 3.30M/41.5M [01:22<37:16, 17.9kB/s]
8%|7 | 3.31M/41.5M [01:22<38:32, 17.3kB/s]
8%|8 | 3.32M/41.5M [01:23<45:32, 14.6kB/s]
8%|8 | 3.34M/41.5M [01:23<29:32, 22.6kB/s]
8%|8 | 3.34M/41.5M [01:24<36:30, 18.3kB/s]
8%|8 | 3.36M/41.5M [01:24<26:42, 25.0kB/s]
8%|8 | 3.37M/41.5M [01:26<45:05, 14.8kB/s]
8%|8 | 3.38M/41.5M [01:26<31:24, 21.2kB/s]
8%|8 | 3.39M/41.5M [01:26<29:51, 22.3kB/s]
8%|8 | 3.40M/41.5M [01:27<27:41, 24.0kB/s]
8%|8 | 3.41M/41.5M [01:27<25:55, 25.7kB/s]
8%|8 | 3.41M/41.5M [01:27<24:32, 27.1kB/s]
8%|8 | 3.42M/41.5M [01:27<23:30, 28.3kB/s]
8%|8 | 3.43M/41.5M [01:28<22:43, 29.3kB/s]
8%|8 | 3
.44M/41.5M [01:28<22:08, 30.0kB/s]
8%|8 | 3.45M/41.5M [01:28<20:41, 32.1kB/s]
8%|8 | 3.45M/41.5M [01:28<17:00, 39.1kB/s]
8%|8 | 3.46M/41.5M [01:28<16:43, 39.7kB/s]
8%|8 | 3.47M/41.5M [01:29<16:52, 39.4kB/s]
8%|8 | 3.48M/41.5M [01:29<14:15, 46.6kB/s]
8%|8 | 3.48M/41.5M [01:29<22:21, 29.7kB/s]
8%|8 | 3.50M/41.5M [01:29<16:50, 39.4kB/s]
8%|8 | 3.51M/41.5M [01:30<22:54, 29.0kB/s]
8%|8 | 3.52M/41.5M [01:30<17:44, 37.4kB/s]
9%|8 | 3.53M/41.5M [01:31<18:24, 36.0kB/s]
9%|8 | 3.54M/41.5M [01:31<19:56, 33.3kB/s]
9%|8 | 3.55M/41.5M [01:31<19:06, 34.7kB/s]
9%|8 | 3.55M/41.5M [01:31<19:32, 33.9kB/s]
9%|8 | 3.56M/41.5M [01:33<47:41, 13.9kB/s]
9%|8 | 3.57M/41.5M [01:33<39:58, 16.6kB/s]
9%|8 | 3.58M/41.5M [01:34<46:22, 14.3kB/s]
9%|8 | 3.59M/41.5M [01:34<44:53, 14.
8kB/s]
9%|8 | 3.59M/41.5M [01:35<56:00, 11.8kB/s]
9%|8 | 3.60M/41.5M [01:36<56:34, 11.7kB/s]
9%|8 | 3.61M/41.5M [01:36<48:04, 13.8kB/s]
9%|8 | 3.62M/41.5M [01:37<59:47, 11.1kB/s]
9%|8 | 3.62M/41.5M [01:38<50:43, 13.0kB/s]
9%|8 | 3.63M/41.5M [01:38<39:56, 16.6kB/s]
9%|8 | 3.64M/41.5M [01:38<36:47, 18.0kB/s]
9%|8 | 3.65M/41.5M [01:39<30:10, 21.9kB/s]
9%|8 | 3.66M/41.5M [01:39<25:32, 25.9kB/s]
9%|8 | 3.66M/41.5M [01:39<22:17, 29.7kB/s]
9%|8 | 3.67M/41.5M [01:39<20:00, 33.0kB/s]
9%|8 | 3.68M/41.5M [01:39<18:25, 35.9kB/s]
9%|8 | 3.69M/41.5M [01:39<17:18, 38.2kB/s]
9%|8 | 3.70M/41.5M [01:40<16:31, 40.0kB/s]
9%|8 | 3.71M/41.5M [01:40<12:17, 53.7kB/s]
9%|8 | 3.72M/41.5M [01:40<12:52, 51.3kB/s]
9%|9 | 3.73M/41.5M [01:40<10:34, 62.4kB/s]
9%|9 |
3.74M/41.5M [01:40<11:30, 57.3kB/s]
9%|9 | 3.76M/41.5M [01:41<09:51, 66.9kB/s]
9%|9 | 3.78M/41.5M [01:41<07:34, 87.0kB/s]
9%|9 | 3.80M/41.5M [01:41<06:30, 101kB/s]
9%|9 | 3.83M/41.5M [01:41<05:55, 111kB/s]
9%|9 | 3.85M/41.5M [01:41<05:33, 118kB/s]
9%|9 | 3.89M/41.5M [01:41<04:22, 150kB/s]
9%|9 | 3.92M/41.5M [01:42<04:07, 159kB/s]
10%|9 | 3.97M/41.5M [01:42<03:24, 192kB/s]
10%|9 | 4.01M/41.5M [01:42<03:14, 202kB/s]
10%|9 | 4.06M/41.5M [01:42<02:46, 236kB/s]
10%|9 | 4.12M/41.5M [01:42<02:31, 259kB/s]
10%|# | 4.19M/41.5M [01:43<02:09, 303kB/s]
10%|# | 4.26M/41.5M [01:43<01:57, 333kB/s]
10%|# | 4.34M/41.5M [01:43<01:45, 368kB/s]
11%|# | 4.43M/41.5M [01:43<01:32, 419kB/s]
11%|# | 4.53M/41.5M [01:43<01:24, 461kB/s]
11%|#1 | 4.64M/41.5M [01:44<01:21, 474kB/s]
1
1%|#1 | 4.76M/41.5M [01:44<01:20, 476kB/s]
12%|#1 | 4.80M/41.5M [01:44<01:41, 380kB/s]
12%|#1 | 4.87M/41.5M [01:45<02:36, 246kB/s]
12%|#1 | 4.95M/41.5M [01:45<02:14, 285kB/s]
12%|#2 | 5.05M/41.5M [01:45<01:59, 321kB/s]
12%|#2 | 5.12M/41.5M [01:45<02:05, 303kB/s]
12%|#2 | 5.16M/41.5M [01:46<03:07, 204kB/s]
13%|#2 | 5.24M/41.5M [01:46<03:16, 193kB/s]
13%|#2 | 5.30M/41.5M [01:47<03:43, 170kB/s]
13%|#2 | 5.33M/41.5M [01:47<04:04, 155kB/s]
13%|#2 | 5.37M/41.5M [01:47<04:02, 156kB/s]
13%|#2 | 5.39M/41.5M [01:48<06:38, 95.0kB/s]
13%|#3 | 5.41M/41.5M [01:48<07:04, 89.1kB/s]
13%|#3 | 5.42M/41.5M [01:49<10:43, 58.8kB/s]
13%|#3 | 5.43M/41.5M [01:50<13:42, 46.0kB/s]
13%|#3 | 5.44M/41.5M [01:50<17:01, 37.0kB/s]
13%|#3 | 5.45M/41.5M [01:50<15:04, 41.8kB/s]
13%|#3 | 5.46M/41.5M [01:51<15:48
, 39.8kB/s]
13%|#3 | 5.47M/41.5M [01:51<20:12, 31.1kB/s]
13%|#3 | 5.48M/41.5M [01:52<26:50, 23.4kB/s]
13%|#3 | 5.50M/41.5M [01:53<24:26, 25.7kB/s]
13%|#3 | 5.51M/41.5M [01:53<23:30, 26.7kB/s]
13%|#3 | 5.52M/41.5M [01:55<42:53, 14.7kB/s]
13%|#3 | 5.52M/41.5M [01:56<54:52, 11.5kB/s]
13%|#3 | 5.53M/41.5M [01:56<45:59, 13.7kB/s]
13%|#3 | 5.54M/41.5M [01:57<53:26, 11.8kB/s]
13%|#3 | 5.55M/41.5M [01:58<1:00:17, 10.4kB/s]
13%|#3 | 5.56M/41.5M [01:58<42:23, 14.8kB/s]
13%|#3 | 5.57M/41.5M [01:59<41:37, 15.1kB/s]
13%|#3 | 5.58M/41.5M [01:59<36:00, 17.4kB/s]
13%|#3 | 5.59M/41.5M [02:00<31:37, 19.8kB/s]
13%|#3 | 5.59M/41.5M [02:00<29:10, 21.5kB/s]
14%|#3 | 5.60M/41.5M [02:00<25:32, 24.5kB/s]
14%|#3 | 5.61M/41.5M [02:00<23:48, 26.3kB/s]
14%|#3 | 5.62M/41.5M [02:01<22:33, 27.8kB/s]
14%|#3
| 5.62M/41.5M [02:01<21:39, 28.9kB/s]
14%|#3 | 5.64M/41.5M [02:01<16:59, 36.9kB/s]
14%|#3 | 5.65M/41.5M [02:01<16:48, 37.3kB/s]
14%|#3 | 5.66M/41.5M [02:02<18:21, 34.1kB/s]
14%|#3 | 5.66M/41.5M [02:02<17:48, 35.2kB/s]
14%|#3 | 5.67M/41.5M [02:03<30:03, 20.8kB/s]
14%|#3 | 5.69M/41.5M [02:04<33:59, 18.4kB/s]
14%|#3 | 5.70M/41.5M [02:04<39:52, 15.7kB/s]
14%|#3 | 5.70M/41.5M [02:05<34:39, 18.0kB/s]
14%|#3 | 5.71M/41.5M [02:05<30:36, 20.4kB/s]
14%|#3 | 5.72M/41.5M [02:05<27:32, 22.7kB/s]
14%|#3 | 5.73M/41.5M [02:06<36:19, 17.2kB/s]
14%|#3 | 5.73M/41.5M [02:09<1:29:45, 6.96kB/s]
14%|#3 | 5.74M/41.5M [02:10<1:19:26, 7.86kB/s]
14%|#3 | 5.75M/41.5M [02:11<1:33:48, 6.66kB/s]
14%|#3 | 5.76M/41.5M [02:13<1:39:25, 6.28kB/s]
14%|#3 | 5.77M/41.5M [02:13<1:25:33, 7.30kB/s]
14%|#3 | 5.77M/41.
5M [02:14<1:08:20, 9.13kB/s]
14%|#3 | 5.79M/41.5M [02:14<40:05, 15.6kB/s]
14%|#3 | 5.80M/41.5M [02:14<33:36, 18.6kB/s]
14%|#3 | 5.80M/41.5M [02:14<28:26, 21.9kB/s]
14%|#4 | 5.81M/41.5M [02:15<24:29, 25.5kB/s]
14%|#4 | 5.82M/41.5M [02:15<21:31, 29.0kB/s]
14%|#4 | 5.83M/41.5M [02:15<19:19, 32.2kB/s]
14%|#4 | 5.84M/41.5M [02:15<13:45, 45.3kB/s]
14%|#4 | 5.85M/41.5M [02:15<13:46, 45.2kB/s]
14%|#4 | 5.86M/41.5M [02:15<13:47, 45.1kB/s]
14%|#4 | 5.88M/41.5M [02:16<11:33, 53.9kB/s]
14%|#4 | 5.88M/41.5M [02:16<11:21, 54.8kB/s]
14%|#4 | 5.90M/41.5M [02:16<10:12, 60.9kB/s]
14%|#4 | 5.91M/41.5M [02:16<09:00, 69.0kB/s]
14%|#4 | 5.92M/41.5M [02:16<09:21, 66.4kB/s]
14%|#4 | 5.94M/41.5M [02:17<09:01, 68.8kB/s]
14%|#4 | 5.95M/41.5M [02:17<08:17, 74.9kB/s]
14%|#4 | 5.97M/41.5M [02:17<07:50, 79.2kB/
s]
14%|#4 | 5.98M/41.5M [02:17<07:31, 82.4kB/s]
14%|#4 | 6.00M/41.5M [02:17<07:19, 84.6kB/s]
15%|#4 | 6.02M/41.5M [02:17<06:14, 99.4kB/s]
15%|#4 | 6.04M/41.5M [02:18<06:24, 96.7kB/s]
15%|#4 | 6.05M/41.5M [02:18<06:28, 95.6kB/s]
15%|#4 | 6.08M/41.5M [02:18<05:49, 106kB/s]
15%|#4 | 6.09M/41.5M [02:18<06:02, 102kB/s]
15%|#4 | 6.12M/41.5M [02:18<05:30, 112kB/s]
15%|#4 | 6.14M/41.5M [02:19<05:11, 119kB/s]
15%|#4 | 6.17M/41.5M [02:19<04:29, 137kB/s]
15%|#4 | 6.20M/41.5M [02:19<04:06, 150kB/s]
15%|#5 | 6.23M/41.5M [02:19<03:52, 159kB/s]
15%|#5 | 6.27M/41.5M [02:19<03:26, 179kB/s]
15%|#5 | 6.32M/41.5M [02:19<03:06, 198kB/s]
15%|#5 | 6.37M/41.5M [02:20<03:04, 200kB/s]
15%|#5 | 6.41M/41.5M [02:21<06:53, 88.9kB/s]
15%|#5 | 6.43M/41.5M [02:21<06:47, 90.2kB/s]
16%|#5 | 6.54M/41.5M [
02:21<03:39, 167kB/s]
16%|#5 | 6.56M/41.5M [02:22<04:03, 151kB/s]
16%|#5 | 6.59M/41.5M [02:22<05:34, 109kB/s]
16%|#5 | 6.61M/41.5M [02:22<05:43, 106kB/s]
16%|#5 | 6.63M/41.5M [02:23<05:51, 104kB/s]
16%|#6 | 6.65M/41.5M [02:23<08:10, 74.5kB/s]
16%|#6 | 6.66M/41.5M [02:25<21:22, 28.5kB/s]
16%|#6 | 6.70M/41.5M [02:25<15:18, 39.7kB/s]
16%|#6 | 6.71M/41.5M [02:27<25:00, 24.3kB/s]
16%|#6 | 6.74M/41.5M [02:27<17:28, 34.7kB/s]
16%|#6 | 6.76M/41.5M [02:28<15:47, 38.4kB/s]
16%|#6 | 6.77M/41.5M [02:28<14:19, 42.3kB/s]
16%|#6 | 6.78M/41.5M [02:28<14:58, 40.5kB/s]
16%|#6 | 6.79M/41.5M [02:28<15:37, 38.8kB/s]
16%|#6 | 6.80M/41.5M [02:29<19:55, 30.4kB/s]
16%|#6 | 6.81M/41.5M [02:29<20:07, 30.1kB/s]
16%|#6 | 6.83M/41.5M [02:30<25:26, 23.8kB/s]
16%|#6 | 6.84M/41.5M [02:31<24:10, 25.1kB/s]
16%|
#6 | 6.84M/41.5M [02:31<23:01, 26.3kB/s]
17%|#6 | 6.85M/41.5M [02:31<22:01, 27.5kB/s]
17%|#6 | 6.87M/41.5M [02:31<16:55, 35.7kB/s]
17%|#6 | 6.88M/41.5M [02:32<17:21, 34.9kB/s]
17%|#6 | 6.88M/41.5M [02:32<26:49, 22.5kB/s]
17%|#6 | 6.90M/41.5M [02:33<23:35, 25.6kB/s]
17%|#6 | 6.91M/41.5M [02:33<18:22, 32.9kB/s]
17%|#6 | 6.92M/41.5M [02:34<22:25, 26.9kB/s]
17%|#6 | 6.94M/41.5M [02:34<17:33, 34.4kB/s]
17%|#6 | 6.95M/41.5M [02:35<36:53, 16.4kB/s]
17%|#6 | 6.95M/41.5M [02:36<32:42, 18.4kB/s]
17%|#6 | 6.97M/41.5M [02:36<23:26, 25.7kB/s]
17%|#6 | 6.98M/41.5M [02:36<22:24, 26.9kB/s]
17%|#6 | 6.98M/41.5M [02:36<21:33, 28.0kB/s]
17%|#6 | 6.99M/41.5M [02:37<25:40, 23.5kB/s]
17%|#6 | 7.01M/41.5M [02:38<26:05, 23.1kB/s]
17%|#6 | 7.02M/41.5M [02:38<20:59, 28.7kB/s]
17%|#6 | 7.03M/41.5M [02:
39<36:29, 16.5kB/s]
17%|#6 | 7.04M/41.5M [02:40<32:22, 18.6kB/s]
17%|#6 | 7.05M/41.5M [02:40<28:58, 20.8kB/s]
17%|#7 | 7.05M/41.5M [02:40<30:17, 19.9kB/s]
17%|#7 | 7.07M/41.5M [02:41<32:31, 18.5kB/s]
17%|#7 | 7.08M/41.5M [02:42<43:22, 13.9kB/s]
17%|#7 | 7.09M/41.5M [02:43<37:10, 16.2kB/s]
17%|#7 | 7.09M/41.5M [02:43<37:14, 16.1kB/s]
17%|#7 | 7.10M/41.5M [02:44<37:18, 16.1kB/s]
17%|#7 | 7.11M/41.5M [02:44<37:22, 16.1kB/s]
17%|#7 | 7.12M/41.5M [02:45<37:23, 16.1kB/s]
17%|#7 | 7.12M/41.5M [02:45<37:25, 16.0kB/s]
17%|#7 | 7.13M/41.5M [02:46<48:24, 12.4kB/s]
17%|#7 | 7.14M/41.5M [02:46<39:37, 15.1kB/s]
17%|#7 | 7.15M/41.5M [02:47<38:58, 15.4kB/s]
17%|#7 | 7.16M/41.5M [02:48<44:05, 13.6kB/s]
17%|#7 | 7.16M/41.5M [02:48<47:40, 12.6kB/s]
17%|#7 | 7.17M/41.5M [02:49<39:00, 15.4kB/s]
17%
|#7 | 7.18M/41.5M [02:49<38:32, 15.6kB/s]
17%|#7 | 7.19M/41.5M [02:50<35:52, 16.7kB/s]
17%|#7 | 7.20M/41.5M [02:50<29:06, 20.6kB/s]
17%|#7 | 7.20M/41.5M [02:50<28:22, 21.1kB/s]
17%|#7 | 7.21M/41.5M [02:50<23:51, 25.1kB/s]
17%|#7 | 7.22M/41.5M [02:51<24:41, 24.2kB/s]
17%|#7 | 7.23M/41.5M [02:51<16:22, 36.6kB/s]
17%|#7 | 7.24M/41.5M [02:51<16:20, 36.6kB/s]
17%|#7 | 7.25M/41.5M [02:51<15:32, 38.5kB/s]
17%|#7 | 7.26M/41.5M [02:51<14:56, 40.1kB/s]
18%|#7 | 7.27M/41.5M [02:52<13:39, 43.8kB/s]
18%|#7 | 7.27M/41.5M [02:52<13:33, 44.1kB/s]
18%|#7 | 7.29M/41.5M [02:52<11:06, 53.8kB/s]
18%|#7 | 7.30M/41.5M [02:52<11:38, 51.3kB/s]
18%|#7 | 7.30M/41.5M [02:52<11:18, 52.8kB/s]
18%|#7 | 7.32M/41.5M [02:53<09:19, 64.0kB/s]
18%|#7 | 7.34M/41.5M [02:53<08:18, 71.8kB/s]
18%|#7 | 7.35M/41.5M [02
:53<08:14, 72.4kB/s]
18%|#7 | 7.36M/41.5M [02:53<08:39, 68.9kB/s]
18%|#7 | 7.38M/41.5M [02:53<07:54, 75.3kB/s]
18%|#7 | 7.39M/41.5M [02:53<07:28, 79.7kB/s]
18%|#7 | 7.41M/41.5M [02:54<07:11, 82.8kB/s]
18%|#7 | 7.42M/41.5M [02:54<07:00, 84.9kB/s]
18%|#7 | 7.45M/41.5M [02:54<05:57, 99.9kB/s]
18%|#7 | 7.46M/41.5M [02:54<06:08, 96.9kB/s]
18%|#8 | 7.48M/41.5M [02:54<05:29, 108kB/s]
18%|#8 | 7.51M/41.5M [02:55<05:06, 116kB/s]
18%|#8 | 7.54M/41.5M [02:55<04:23, 135kB/s]
18%|#8 | 7.57M/41.5M [02:55<03:59, 148kB/s]
18%|#8 | 7.61M/41.5M [02:55<03:27, 171kB/s]
18%|#8 | 7.66M/41.5M [02:55<02:56, 201kB/s]
19%|#8 | 7.70M/41.5M [02:55<02:41, 219kB/s]
19%|#8 | 7.75M/41.5M [02:56<02:21, 249kB/s]
19%|#8 | 7.80M/41.5M [02:56<02:20, 251kB/s]
19%|#8 | 7.83M/41.5M [02:58<10:55, 53.8kB/s]
19%|#8
| 7.88M/41.5M [02:58<08:15, 71.1kB/s]
19%|#9 | 8.01M/41.5M [02:59<05:19, 110kB/s]
19%|#9 | 8.05M/41.5M [03:00<06:02, 96.8kB/s]
19%|#9 | 8.07M/41.5M [03:00<06:20, 92.2kB/s]
20%|#9 | 8.18M/41.5M [03:00<03:50, 151kB/s]
20%|#9 | 8.20M/41.5M [03:00<04:07, 141kB/s]
20%|#9 | 8.23M/41.5M [03:01<07:05, 82.0kB/s]
20%|#9 | 8.30M/41.5M [03:03<08:06, 71.6kB/s]
20%|## | 8.31M/41.5M [03:03<08:12, 70.6kB/s]
20%|## | 8.34M/41.5M [03:04<11:03, 52.4kB/s]
20%|## | 8.42M/41.5M [03:04<06:16, 92.1kB/s]
20%|## | 8.45M/41.5M [03:04<06:26, 89.7kB/s]
20%|## | 8.46M/41.5M [03:05<08:00, 72.1kB/s]
20%|## | 8.49M/41.5M [03:05<07:00, 82.2kB/s]
21%|## | 8.51M/41.5M [03:05<07:20, 78.5kB/s]
21%|## | 8.52M/41.5M [03:06<07:39, 75.3kB/s]
21%|## | 8.55M/41.5M [03:06<07:10, 80.3kB/s]
21%|## | 8.56M/41.5M [03:06<09:3
0, 60.5kB/s]
21%|## | 8.59M/41.5M [03:07<10:18, 55.8kB/s]
21%|## | 8.61M/41.5M [03:08<12:17, 46.7kB/s]
21%|## | 8.62M/41.5M [03:08<15:37, 36.7kB/s]
21%|## | 8.63M/41.5M [03:09<15:56, 36.0kB/s]
21%|## | 8.64M/41.5M [03:09<16:16, 35.3kB/s]
21%|## | 8.65M/41.5M [03:09<16:35, 34.6kB/s]
21%|## | 8.66M/41.5M [03:09<16:52, 34.0kB/s]
21%|## | 8.66M/41.5M [03:10<21:20, 26.9kB/s]
21%|## | 8.67M/41.5M [03:11<27:07, 21.1kB/s]
21%|## | 8.68M/41.5M [03:11<24:40, 23.2kB/s]
21%|## | 8.69M/41.5M [03:11<25:23, 22.6kB/s]
21%|## | 8.70M/41.5M [03:12<23:16, 24.6kB/s]
21%|## | 8.70M/41.5M [03:12<21:43, 26.4kB/s]
21%|## | 8.71M/41.5M [03:13<30:59, 18.5kB/s]
21%|##1 | 8.72M/41.5M [03:13<27:08, 21.1kB/s]
21%|##1 | 8.73M/41.5M [03:13<24:23, 23.5kB/s]
21%|##1 | 8.73M/41.5M [03:13<22:26, 25.5kB/s]
21%|##1
| 8.74M/41.5M [03:14<31:42, 18.1kB/s]
21%|##1 | 8.76M/41.5M [03:14<21:13, 27.0kB/s]
21%|##1 | 8.77M/41.5M [03:15<34:24, 16.6kB/s]
21%|##1 | 8.78M/41.5M [03:16<27:32, 20.8kB/s]
21%|##1 | 8.79M/41.5M [03:16<25:18, 22.6kB/s]
21%|##1 | 8.80M/41.5M [03:16<23:28, 24.3kB/s]
21%|##1 | 8.80M/41.5M [03:17<21:59, 26.0kB/s]
21%|##1 | 8.81M/41.5M [03:17<20:51, 27.4kB/s]
21%|##1 | 8.82M/41.5M [03:18<38:50, 14.7kB/s]
21%|##1 | 8.84M/41.5M [03:19<30:23, 18.8kB/s]
21%|##1 | 8.84M/41.5M [03:19<27:21, 20.9kB/s]
21%|##1 | 8.85M/41.5M [03:19<28:28, 20.0kB/s]
21%|##1 | 8.87M/41.5M [03:20<28:31, 20.0kB/s]
21%|##1 | 8.88M/41.5M [03:21<37:31, 15.2kB/s]
21%|##1 | 8.88M/41.5M [03:21<32:37, 17.5kB/s]
21%|##1 | 8.89M/41.5M [03:22<38:04, 15.0kB/s]
21%|##1 | 8.90M/41.5M [03:23<46:02, 12.4kB/s]
21%|##1 | 8.91M/41.5M [03:23<38:
07, 14.9kB/s]
21%|##1 | 8.91M/41.5M [03:24<37:23, 15.2kB/s]
22%|##1 | 8.92M/41.5M [03:24<31:41, 18.0kB/s]
22%|##1 | 8.93M/41.5M [03:24<27:36, 20.6kB/s]
22%|##1 | 8.94M/41.5M [03:25<24:41, 23.0kB/s]
22%|##1 | 8.95M/41.5M [03:25<22:37, 25.1kB/s]
22%|##1 | 8.95M/41.5M [03:25<25:51, 22.0kB/s]
22%|##1 | 8.97M/41.5M [03:26<19:47, 28.7kB/s]
22%|##1 | 8.98M/41.5M [03:26<18:01, 31.5kB/s]
22%|##1 | 8.98M/41.5M [03:26<16:36, 34.2kB/s]
22%|##1 | 9.00M/41.5M [03:26<12:49, 44.3kB/s]
22%|##1 | 9.01M/41.5M [03:27<12:06, 46.9kB/s]
22%|##1 | 9.02M/41.5M [03:27<12:14, 46.4kB/s]
22%|##1 | 9.02M/41.5M [03:27<12:20, 46.0kB/s]
22%|##1 | 9.04M/41.5M [03:27<09:44, 58.2kB/s]
22%|##1 | 9.05M/41.5M [03:27<10:25, 54.4kB/s]
22%|##1 | 9.06M/41.5M [03:27<08:45, 64.7kB/s]
22%|##1 | 9.08M/41.5M [03:28<08:23, 67.6kB/s]
22%|##1
| 9.09M/41.5M [03:28<08:40, 65.3kB/s]
22%|##1 | 9.10M/41.5M [03:28<08:18, 68.1kB/s]
22%|##1 | 9.11M/41.5M [03:28<08:36, 65.8kB/s]
22%|##1 | 9.12M/41.5M [03:28<07:44, 73.1kB/s]
22%|##2 | 9.14M/41.5M [03:29<07:13, 78.2kB/s]
22%|##2 | 9.16M/41.5M [03:29<06:54, 81.7kB/s]
22%|##2 | 9.18M/41.5M [03:29<06:10, 91.5kB/s]
22%|##2 | 9.20M/41.5M [03:29<06:12, 91.0kB/s]
22%|##2 | 9.21M/41.5M [03:29<05:48, 97.0kB/s]
22%|##2 | 9.23M/41.5M [03:30<05:32, 102kB/s]
22%|##2 | 9.25M/41.5M [03:30<05:21, 105kB/s]
22%|##2 | 9.27M/41.5M [03:30<05:16, 107kB/s]
22%|##2 | 9.29M/41.5M [03:30<05:09, 109kB/s]
22%|##2 | 9.31M/41.5M [03:30<04:48, 117kB/s]
23%|##2 | 9.34M/41.5M [03:30<04:35, 122kB/s]
23%|##2 | 9.36M/41.5M [03:31<04:27, 126kB/s]
23%|##2 | 9.39M/41.5M [03:31<04:12, 133kB/s]
23%|##2 | 9.41M/41.5M [03:31<03:54, 14
3kB/s]
23%|##2 | 9.45M/41.5M [03:31<03:37, 154kB/s]
23%|##2 | 9.48M/41.5M [03:31<03:27, 162kB/s]
23%|##2 | 9.52M/41.5M [03:32<03:06, 180kB/s]
23%|##3 | 9.55M/41.5M [03:32<02:44, 204kB/s]
23%|##3 | 9.58M/41.5M [03:32<03:03, 182kB/s]
23%|##3 | 9.61M/41.5M [03:32<02:52, 194kB/s]
23%|##3 | 9.63M/41.5M [03:32<04:13, 132kB/s]
23%|##3 | 9.65M/41.5M [03:33<09:45, 57.1kB/s]
23%|##3 | 9.73M/41.5M [03:34<04:50, 115kB/s]
24%|##3 | 9.77M/41.5M [03:34<04:43, 117kB/s]
24%|##3 | 9.79M/41.5M [03:35<07:01, 78.8kB/s]
24%|##3 | 9.82M/41.5M [03:35<06:16, 88.3kB/s]
24%|##3 | 9.86M/41.5M [03:35<05:19, 104kB/s]
24%|##3 | 9.88M/41.5M [03:35<05:25, 102kB/s]
24%|##3 | 9.91M/41.5M [03:36<05:05, 108kB/s]
24%|##3 | 9.94M/41.5M [03:36<05:14, 105kB/s]
24%|##3 | 9.95M/41.5M [03:37<11:59, 46.0kB/s]
24%|##4 | 9.98M/41.5M
[03:37<09:18, 59.2kB/s]
24%|##4 | 10.0M/41.5M [03:38<08:19, 66.1kB/s]
24%|##4 | 10.0M/41.5M [03:39<13:40, 40.2kB/s]
24%|##4 | 10.0M/41.5M [03:39<13:00, 42.3kB/s]
24%|##4 | 10.1M/41.5M [03:39<11:35, 47.4kB/s]
24%|##4 | 10.1M/41.5M [03:40<17:06, 32.1kB/s]
24%|##4 | 10.1M/41.5M [03:41<22:47, 24.1kB/s]
24%|##4 | 10.1M/41.5M [03:41<18:12, 30.1kB/s]
24%|##4 | 10.1M/41.5M [03:41<18:00, 30.5kB/s]
24%|##4 | 10.1M/41.5M [03:42<21:26, 25.6kB/s]
24%|##4 | 10.1M/41.5M [03:42<16:36, 33.0kB/s]
24%|##4 | 10.1M/41.5M [03:43<23:57, 22.9kB/s]
24%|##4 | 10.1M/41.5M [03:43<18:08, 30.2kB/s]
24%|##4 | 10.2M/41.5M [03:43<17:55, 30.5kB/s]
25%|##4 | 10.2M/41.5M [03:44<14:23, 38.0kB/s]
25%|##4 | 10.2M/41.5M [03:44<14:57, 36.6kB/s]
25%|##4 | 10.2M/41.5M [03:44<12:31, 43.6kB/s]
25%|##4 | 10.2M/41.5M [03:44<13:29, 40.5kB/s]
25%|##4 | 10.2M/41.5M [03:45<14:18, 38.2kB/s]
25%|##4 | 10.2M/41.5M [03:45<15:55, 34.3kB/s]
25%|##4 | 10.2M/41.5M [03:45<15:36, 35.0kB/s]
25%|##4 | 10.2M/41.5M [03:46<13:21, 40.9kB/s]
25%|##4 | 10.3M/41.5M [03:46<13:36, 40.1kB/s]
25%|##4 | 10.3M/41.5M [03:46<18:27, 29.6kB/s]
25%|##4 | 10.3M/41.5M [03:47<14:26, 37.7kB/s]
25%|##4 | 10.3M/41.5M [03:47<15:00, 36.3kB/s]
25%|##4 | 10.3M/41.5M [03:48<20:15, 26.9kB/s]
25%|##4 | 10.3M/41.5M [03:48<18:45, 29.1kB/s]
25%|##4 | 10.3M/41.5M [03:49<36:20, 15.0kB/s]
25%|##4 | 10.3M/41.5M [03:50<27:56, 19.5kB/s]
25%|##4 | 10.3M/41.5M [03:50<32:33, 16.7kB/s]
25%|##4 | 10.3M/41.5M [03:51<40:36, 13.4kB/s]
25%|##4 | 10.4M/41.5M [03:54<1:04:07, 8.48kB/s]
25%|##4 | 10.4M/41.5M [03:54<53:15, 10.2kB/s]
25%|##5 | 10.4M/41.5M [03:55<48:29, 11.2kB/s]
25%|##5 | 10.4M/
41.5M [03:55<40:15, 13.5kB/s]
25%|##5 | 10.4M/41.5M [03:56<43:09, 12.6kB/s]
25%|##5 | 10.4M/41.5M [03:57<44:19, 12.3kB/s]
25%|##5 | 10.4M/41.5M [03:59<1:08:22, 7.94kB/s]
25%|##5 | 10.4M/41.5M [04:00<1:08:14, 7.96kB/s]
25%|##5 | 10.4M/41.5M [04:00<1:02:07, 8.74kB/s]
25%|##5 | 10.4M/41.5M [04:01<49:50, 10.9kB/s]
25%|##5 | 10.4M/41.5M [04:01<44:02, 12.3kB/s]
25%|##5 | 10.4M/41.5M [04:02<43:57, 12.3kB/s]
25%|##5 | 10.5M/41.5M [04:02<35:16, 15.4kB/s]
25%|##5 | 10.5M/41.5M [04:02<28:19, 19.1kB/s]
25%|##5 | 10.5M/41.5M [04:02<26:14, 20.7kB/s]
25%|##5 | 10.5M/41.5M [04:03<22:50, 23.7kB/s]
25%|##5 | 10.5M/41.5M [04:03<18:45, 28.9kB/s]
25%|##5 | 10.5M/41.5M [04:03<16:44, 32.4kB/s]
25%|##5 | 10.5M/41.5M [04:03<16:10, 33.5kB/s]
25%|##5 | 10.5M/41.5M [04:03<14:56, 36.2kB/s]
25%|##5 | 10.5M/41.5M [04:04<14:04,
38.5kB/s]
25%|##5 | 10.5M/41.5M [04:04<12:36, 42.9kB/s]
25%|##5 | 10.5M/41.5M [04:04<10:50, 49.9kB/s]
25%|##5 | 10.5M/41.5M [04:04<10:01, 53.9kB/s]
25%|##5 | 10.5M/41.5M [04:04<10:38, 50.8kB/s]
25%|##5 | 10.6M/41.5M [04:04<09:23, 57.6kB/s]
25%|##5 | 10.6M/41.5M [04:05<09:05, 59.4kB/s]
26%|##5 | 10.6M/41.5M [04:05<07:48, 69.1kB/s]
26%|##5 | 10.6M/41.5M [04:05<07:40, 70.3kB/s]
26%|##5 | 10.6M/41.5M [04:05<07:05, 76.1kB/s]
26%|##5 | 10.6M/41.5M [04:05<06:43, 80.2kB/s]
26%|##5 | 10.6M/41.5M [04:05<06:29, 83.1kB/s]
26%|##5 | 10.7M/41.5M [04:06<06:19, 85.1kB/s]
26%|##5 | 10.7M/41.5M [04:06<06:13, 86.5kB/s]
26%|##5 | 10.7M/41.5M [04:06<05:42, 94.3kB/s]
26%|##5 | 10.7M/41.5M [04:06<05:14, 103kB/s]
26%|##5 | 10.7M/41.5M [04:06<05:12, 103kB/s]
26%|##5 | 10.7M/41.5M [04:06<04:52, 110kB/s]
26%|##5 |
10.8M/41.5M [04:07<05:11, 103kB/s]
26%|##5 | 10.8M/41.5M [04:07<04:43, 114kB/s]
26%|##6 | 10.8M/41.5M [04:07<04:06, 130kB/s]
26%|##6 | 10.8M/41.5M [04:07<03:39, 147kB/s]
26%|##6 | 10.9M/41.5M [04:07<02:56, 182kB/s]
26%|##6 | 10.9M/41.5M [04:07<03:09, 170kB/s]
26%|##6 | 10.9M/41.5M [04:07<03:06, 172kB/s]
26%|##6 | 10.9M/41.5M [04:08<02:48, 190kB/s]
26%|##6 | 11.0M/41.5M [04:08<02:22, 225kB/s]
27%|##6 | 11.0M/41.5M [04:08<02:28, 215kB/s]
27%|##6 | 11.0M/41.5M [04:08<02:18, 230kB/s]
27%|##6 | 11.1M/41.5M [04:08<02:27, 216kB/s]
27%|##6 | 11.1M/41.5M [04:09<03:56, 135kB/s]
27%|##6 | 11.2M/41.5M [04:09<03:05, 171kB/s]
27%|##7 | 11.2M/41.5M [04:09<03:01, 175kB/s]
27%|##7 | 11.3M/41.5M [04:09<02:28, 213kB/s]
27%|##7 | 11.3M/41.5M [04:10<05:46, 91.3kB/s]
27%|##7 | 11.4M/41.5M [04:11<04:05, 129kB/s]
27
%|##7 | 11.4M/41.5M [04:11<05:14, 100kB/s]
28%|##7 | 11.4M/41.5M [04:12<07:10, 73.2kB/s]
28%|##7 | 11.5M/41.5M [04:12<05:16, 99.5kB/s]
28%|##7 | 11.5M/41.5M [04:12<05:40, 92.4kB/s]
28%|##7 | 11.5M/41.5M [04:13<06:04, 86.2kB/s]
28%|##7 | 11.5M/41.5M [04:13<08:01, 65.2kB/s]
28%|##7 | 11.5M/41.5M [04:13<08:03, 65.0kB/s]
28%|##7 | 11.5M/41.5M [04:14<08:04, 64.8kB/s]
28%|##7 | 11.6M/41.5M [04:15<15:46, 33.2kB/s]
28%|##7 | 11.6M/41.5M [04:15<18:17, 28.6kB/s]
28%|##7 | 11.6M/41.5M [04:16<15:26, 33.8kB/s]
28%|##7 | 11.6M/41.5M [04:16<13:28, 38.7kB/s]
28%|##8 | 11.6M/41.5M [04:17<24:23, 21.4kB/s]
28%|##8 | 11.6M/41.5M [04:18<25:16, 20.6kB/s]
28%|##8 | 11.6M/41.5M [04:18<27:32, 18.9kB/s]
28%|##8 | 11.6M/41.5M [04:19<28:07, 18.5kB/s]
28%|##8 | 11.7M/41.5M [04:20<26:20, 19.8kB/s]
28%|##8 | 11.7M/41.5M [04
:21<38:17, 13.6kB/s]
28%|##8 | 11.7M/41.5M [04:21<32:47, 15.9kB/s]
28%|##8 | 11.7M/41.5M [04:22<32:43, 15.9kB/s]
28%|##8 | 11.7M/41.5M [04:22<30:06, 17.3kB/s]
28%|##8 | 11.7M/41.5M [04:22<24:54, 20.9kB/s]
28%|##8 | 11.7M/41.5M [04:22<21:05, 24.7kB/s]
28%|##8 | 11.7M/41.5M [04:23<18:20, 28.4kB/s]
28%|##8 | 11.7M/41.5M [04:23<16:21, 31.8kB/s]
28%|##8 | 11.7M/41.5M [04:23<14:56, 34.8kB/s]
28%|##8 | 11.7M/41.5M [04:23<13:56, 37.3kB/s]
28%|##8 | 11.7M/41.5M [04:23<13:13, 39.3kB/s]
28%|##8 | 11.8M/41.5M [04:23<12:43, 40.8kB/s]
28%|##8 | 11.8M/41.5M [04:24<12:22, 42.0kB/s]
28%|##8 | 11.8M/41.5M [04:24<09:20, 55.6kB/s]
28%|##8 | 11.8M/41.5M [04:24<09:52, 52.5kB/s]
28%|##8 | 11.8M/41.5M [04:24<08:10, 63.5kB/s]
28%|##8 | 11.8M/41.5M [04:24<07:17, 71.2kB/s]
29%|##8 | 11.8M/41.5M [04:25<06:45, 76.7kB/s]
29
%|##8 | 11.8M/41.5M [04:25<07:41, 67.3kB/s]
29%|##8 | 11.9M/41.5M [04:25<06:59, 74.0kB/s]
29%|##8 | 11.9M/41.5M [04:25<06:34, 78.7kB/s]
29%|##8 | 11.9M/41.5M [04:25<06:18, 82.1kB/s]
29%|##8 | 11.9M/41.5M [04:25<06:07, 84.4kB/s]
29%|##8 | 11.9M/41.5M [04:26<05:11, 99.5kB/s]
29%|##8 | 11.9M/41.5M [04:26<05:20, 96.6kB/s]
29%|##8 | 12.0M/41.5M [04:26<04:46, 108kB/s]
29%|##8 | 12.0M/41.5M [04:26<03:58, 130kB/s]
29%|##8 | 12.0M/41.5M [04:26<03:33, 145kB/s]
29%|##9 | 12.1M/41.5M [04:27<03:18, 155kB/s]
29%|##9 | 12.1M/41.5M [04:27<02:55, 176kB/s]
29%|##9 | 12.1M/41.5M [04:27<02:30, 204kB/s]
29%|##9 | 12.2M/41.5M [04:27<02:09, 237kB/s]
30%|##9 | 12.2M/41.5M [04:27<01:57, 260kB/s]
30%|##9 | 12.3M/41.5M [04:28<01:45, 290kB/s]
30%|##9 | 12.4M/41.5M [04:28<01:34, 324kB/s]
30%|### | 12.5M/41.5M [04:28<01:2
4, 362kB/s]
30%|### | 12.5M/41.5M [04:28<01:15, 402kB/s]
30%|### | 12.6M/41.5M [04:28<01:10, 430kB/s]
31%|### | 12.7M/41.5M [04:28<01:03, 476kB/s]
31%|### | 12.9M/41.5M [04:29<00:56, 535kB/s]
31%|###1 | 13.0M/41.5M [04:29<00:50, 590kB/s]
32%|###1 | 13.1M/41.5M [04:29<00:46, 642kB/s]
32%|###1 | 13.3M/41.5M [04:29<00:41, 706kB/s]
32%|###2 | 13.4M/41.5M [04:29<00:38, 764kB/s]
33%|###2 | 13.6M/41.5M [04:30<00:35, 831kB/s]
33%|###3 | 13.8M/41.5M [04:30<00:32, 905kB/s]
34%|###3 | 14.0M/41.5M [04:30<00:29, 971kB/s]
34%|###4 | 14.2M/41.5M [04:30<00:27, 1.06MB/s]
35%|###4 | 14.4M/41.5M [04:30<00:25, 1.13MB/s]
35%|###5 | 14.7M/41.5M [04:30<00:23, 1.22MB/s]
36%|###5 | 14.9M/41.5M [04:31<00:21, 1.31MB/s]
37%|###6 | 15.2M/41.5M [04:31<00:19, 1.41MB/s]
37%|###7 | 15.5M/41.5M [04:31<00:18, 1.51MB/s]
38%|###8 | 15.8M/
41.5M [04:31<00:16, 1.61MB/s]
39%|###8 | 16.2M/41.5M [04:31<00:15, 1.72MB/s]
40%|###9 | 16.5M/41.5M [04:32<00:14, 1.84MB/s]
41%|#### | 16.9M/41.5M [04:32<00:13, 1.93MB/s]
42%|####1 | 17.3M/41.5M [04:32<00:12, 2.05MB/s]
43%|####2 | 17.8M/41.5M [04:32<00:11, 2.18MB/s]
44%|####3 | 18.2M/41.5M [04:32<00:10, 2.32MB/s]
45%|####5 | 18.7M/41.5M [04:32<00:09, 2.47MB/s]
46%|####6 | 19.2M/41.5M [04:33<00:08, 2.62MB/s]
48%|####7 | 19.8M/41.5M [04:33<00:08, 2.77MB/s]
49%|####9 | 20.3M/41.5M [04:33<00:07, 2.93MB/s]
50%|##### | 20.9M/41.5M [04:33<00:06, 3.09MB/s]
52%|#####2 | 21.6M/41.5M [04:33<00:06, 3.27MB/s]
54%|#####3 | 22.2M/41.5M [04:34<00:05, 3.43MB/s]
55%|#####5 | 23.0M/41.5M [04:34<00:05, 3.63MB/s]
57%|#####7 | 23.7M/41.5M [04:34<00:04, 4.20MB/s]
59%|#####8 | 24.4M/41.5M [04:34<00:03, 4.58MB/s]
60%|###### | 24.9M/41.5M [04:34<00:03, 4.58MB/s
]
61%|######1 | 25.4M/41.5M [04:34<00:04, 3.92MB/s]
63%|######3 | 26.2M/41.5M [04:34<00:03, 4.15MB/s]
65%|######5 | 27.0M/41.5M [04:35<00:02, 5.24MB/s]
67%|######7 | 27.8M/41.5M [04:35<00:02, 5.89MB/s]
69%|######8 | 28.5M/41.5M [04:35<00:02, 5.16MB/s]
70%|######9 | 29.0M/41.5M [04:35<00:02, 4.50MB/s]
72%|#######2 | 30.0M/41.5M [04:35<00:02, 5.27MB/s]
75%|#######4 | 31.0M/41.5M [04:35<00:01, 6.44MB/s]
76%|#######6 | 31.6M/41.5M [04:35<00:01, 6.14MB/s]
78%|#######7 | 32.3M/41.5M [04:36<00:01, 5.28MB/s]
80%|######## | 33.3M/41.5M [04:36<00:01, 6.03MB/s]
83%|########3 | 34.5M/41.5M [04:36<00:00, 7.37MB/s]
85%|########4 | 35.2M/41.5M [04:36<00:00, 7.01MB/s]
87%|########6 | 36.0M/41.5M [04:36<00:00, 6.01MB/s]
89%|########9 | 37.1M/41.5M [04:36<00:00, 7.24MB/s]
92%|#########2| 38.4M/41.5M [04:36<00:00, 8.48MB/s]
95%|#########4| 39.2M/41.5M [04:36<00:00, 7.69MB/s]
97%|#########6| 40.0M
/41.5M [04:37<00:00, 6.62MB/s]
100%|#########9| 41.4M/41.5M [04:37<00:00, 8.11MB/s]
100%|##########| 41.5M/41.5M [04:37<00:00, 157kB/s]
@@ -283,6 +283,11 @@ Look up prediction top 1 index in 1000 class synset.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 5 minutes 1.922 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 e794d02fe..c5e1d6732 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -201,7 +201,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 17.120 seconds)
+ **Total running time of the script:** ( 1 minutes 4.765 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 554dc3e8b..cb85cc01e 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]
41%|#### | 18.2M/44.7M [00:00<00:00, 191MB/s]
96%|#########5| 42.8M/44.7M [00:00<00:00, 230MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 226MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
32%|###1 | 14.1M/44.7M [00:00<00:00, 148MB/s]
79%|#######9 | 35.4M/44.7M [00:00<00:00, 192MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 194MB/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 dc0c5e876..253ab43d6 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -372,7 +372,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 2.725 seconds)
+ **Total running time of the script:** ( 1 minutes 0.290 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 a2eac4273..bb8c6c4ab 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
=================
-**05:34.942** total execution time for **how_to_compile_models** files:
+**09:45.416** total execution time for **how_to_compile_models** files:
-- **01:17.120**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
-- **01:02.725**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
-- **00:58.027**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
-- **00:31.309**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
-- **00:24.932**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
-- **00:22.362**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
-- **00:21.784**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
-- **00:20.117**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
-- **00:13.761**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
-- **00:02.806**: :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``)
+- **05:01.922**: :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``)
+- **01:04.765**: :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``)
+- **01:00.290**: :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``)
+- **00:56.720**: :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``)
+- **00:24.256**: :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``)
+- **00:21.236**: :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``)
+- **00:21.104**: :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``)
+- **00:19.170**: :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``)
+- **00:13.492**: :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``)
+- **00:02.460**: :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 afa0693df..8bae1b5bb 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -393,7 +393,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.8464 16.6414 17.4895 16.4227 0.3974
+ 15.9522 15.9067 16.2504 15.7817 0.1391
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 bbd676c52..b637c5ae0 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]
3%|2 | 4.47M/170M [00:00<00:03, 46.7MB/s]
5%|5 | 8.93M/170M [00:00<00:03, 44.9MB/s]
16%|#6 | 27.5M/170M [00:00<00:01, 111MB/s]
31%|###1 | 52.9M/170M [00:00<00:00, 172MB/s]
45%|####4 | 75.8M/170M [00:00<00:00, 196MB/s]
59%|#####8 | 99.4M/170M [00:00<00:00, 214MB/s]
72%|#######1 | 122M/170M [00:00<00:00, 221MB/s]
85%|########5 | 144M/170M [00:00<00:00, 226MB/s]
98%|#########8| 167M/170M [00:00<00:00, 227MB/s]
100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%|1 | 1.79M/170M [00:00<00:09, 18.7MB/s]
2%|2 | 4.23M/170M [00:00<00:07, 22.7MB/s]
9%|9 | 16.1M/170M [00:00<00:02, 69.0MB/s]
17%|#6 | 28.1M/170M [00:00<00:01, 91.6MB/s]
22%|##1 | 36.8M/170M [00:00<00:01, 90.0MB/s]
28%|##7 | 47.5M/170M [00:00<00:01, 97.4MB/s]
33%|###3 | 56.8M/170M [00:00<00:01, 94.9MB/s]
39%|###9 | 66.7M/170M [00:00<00:01, 97.3MB/s]
46%|####6 | 78.7M/170M [00:00<00:00, 106MB/s]
53%|#####3 | 90.1M/170M [00:01<00:00, 110MB/s]
59%|#####9 | 101M/170M [00:01<00:01, 69.2MB/s]
64%|######4 | 109M/170M [00:01<00:01, 45.3MB/s]
71%|#######1 | 121M/170M [00:01<00:00, 58.1MB/s]
78%|#######8 | 133M/170M [00:01<00:00, 70.7MB/s]
86%|########5 | 145M/170M [00:01<00:00, 82.6MB/s]
93%|#########2| 157M/170M [00:02<00:00, 92.6MB/s]
100%|#########9| 169M/170M [00:02<00:00, 101MB/s]
1
00%|##########| 170M/170M [00:02<00:00, 80.8MB/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').
@@ -253,7 +253,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 3 minutes 13.089 seconds)
+ **Total running time of the script:** ( 3 minutes 3.865 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 ae7ed5ac0..07a0ead05 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, 177MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
15%|#4 | 2.02M/13.6M [00:00<00:00, 21.2MB/s]
31%|### | 4.14M/13.6M [00:00<00:00, 21.7MB/s]
48%|####8 | 6.53M/13.6M [00:00<00:00, 23.2MB/s]
83%|########3 | 11.3M/13.6M [00:00<00:00, 33.5MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 32.0MB/s]
@@ -344,7 +344,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.6283 90.5904 92.5449 90.1969 0.3440
+ 90.2609 90.1858 91.2121 90.0475 0.2098
@@ -384,7 +384,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 7.973 seconds)
+ **Total running time of the script:** ( 1 minutes 5.711 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 4e00aa8ad..217f1d468 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -351,7 +351,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.1033 119.0934 121.1836 118.1825 0.4108
+ 121.0642 121.0349 125.7071 120.1228 0.6102
@@ -385,7 +385,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 0.665 seconds)
+ **Total running time of the script:** ( 1 minutes 57.369 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 5df1e1ce1..a792b9f40 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -221,7 +221,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 14.247 seconds)
+ **Total running time of the script:** ( 2 minutes 2.941 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 681dcda75..629e8db61 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]
3%|3 | 4009/132723 [00:00<00:03, 40075.61KB/s]
8%|8 | 11230/132723 [00:00<00:02, 58971.88KB/s]
14%|#4 | 18953/132723 [00:00<00:01, 67302.73KB/s]
20%|## | 26701/132723 [00:00<00:01, 71317.15KB/s]
26%|##6 | 34664/132723 [00:00<00:01, 74313.33KB/s]
32%|###2 | 42671/132723 [00:00<00:01, 76265.96KB/s]
38%|###8 | 50724/132723 [00:00<00:01, 77658.00KB/s]
44%|####4 | 58840/132723 [00:00<00:00, 78768.32KB/s]
50%|##### | 66903/132723 [00:00<00:00, 79338.34KB/s]
57%|#####6 | 75041/132723 [00:01<00:00, 79965.67KB/s]
63%|######2 | 83121/132723 [00:01<00:00, 80219.95KB/s]
69%|######8 | 91271/132723 [00:01<00:00, 80608.23KB/s]
75%|#######4 | 99343/132723 [00:01<00:00, 80640.89KB/s]
81%|######## | 107479/132723 [00:01<00:00, 80851.41KB/s]
87%|########7 | 115565/132723 [00:01<00:00, 80741.23KB/s]
93%|#########
3| 123643/132723 [00:01<00:00, 80751.81KB/s]
99%|#########9| 131719/132723 [00:01<00:00, 80519.12KB/s]
100%|##########| 132723/132723 [00:01<00:00, 77383.60KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6565/132723 [00:00<00:01, 65636.45KB/s]
11%|# | 14591/132723 [00:00<00:01, 74234.52KB/s]
17%|#7 | 22822/132723 [00:00<00:01, 77918.59KB/s]
23%|##3 | 30859/132723 [00:00<00:01, 78882.71KB/s]
29%|##9 | 38933/132723 [00:00<00:01, 79547.86KB/s]
35%|###5 | 46970/132723 [00:00<00:01, 79824.67KB/s]
41%|####1 | 55029/132723 [00:00<00:00, 80073.51KB/s]
48%|####7 | 63090/132723 [00:00<00:00, 80242.61KB/s]
54%|#####3 | 71179/132723 [00:00<00:00, 80442.37KB/s]
60%|#####9 | 79256/132723 [00:01<00:00, 80542.46KB/s]
66%|######5 | 87311/132723 [00:01<00:00, 80510.43KB/s]
72%|#######1 | 95413/132723 [00:01<00:00, 80662.96KB/s]
78%|#######8 | 103563/132723 [00:01<00:00, 80914.39KB/s]
84%|########4 | 111718/132723 [00:01<00:00, 81104.43KB/s]
90%|######### | 119829/132723 [00:01<00:00, 81018.28KB/s]
96%|########
#6| 127977/132723 [00:01<00:00, 81153.79KB/s]
100%|##########| 132723/132723 [00:01<00:00, 80005.35KB/s]
@@ -202,7 +202,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 25.184 seconds)
+ **Total running time of the script:** ( 2 minutes 22.448 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 05018f95f..ddbc56f73 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
=================
-**10:54.397** total execution time for **how_to_deploy_models** files:
+**11:22.976** total execution time for **how_to_deploy_models** files:
-- **03:13.089**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
-- **02:25.184**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
-- **02:00.665**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
-- **01:14.247**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
-- **01:07.973**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
-- **00:29.936**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
-- **00:23.097**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
-- **00:00.206**: :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``)
+- **03:03.865**: :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``)
+- **02:22.448**: :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``)
+- **02:02.941**: :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``)
+- **01:57.369**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``)
+- **01:05.711**: :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``)
+- **00:28.311**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``)
+- **00:22.133**: :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``)
+- **00:00.200**: :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 3c1711d0d..37cd2df1b 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -423,7 +423,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc6017630-3622-447b-bdaf-b8f11e17ab66 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipaf4c81c7-6904-47fb-bed2-21df8c378cec 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 e4d56c5ad..9221ad3e7 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
=================
-**00:38.346** total execution time for **how_to_extend_tvm** files:
+**00:37.991** total execution time for **how_to_extend_tvm** files:
-- **00:34.784**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
-- **00:02.281**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
-- **00:01.070**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
-- **00:00.211**: :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``)
+- **00:34.419**: :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``)
+- **00:02.280**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``)
+- **00:01.084**: :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``)
+- **00:00.208**: :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 a5b515c50..fba3100b9 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: 5982us [5982us] (45.30%; 45.30%)
- FoldScaleAxis: 7221us [2us] (54.70%; 54.70%)
- FoldConstant: 7219us [1503us] (54.68%; 99.97%)
- InferType: 5717us [5717us] (43.30%; 79.18%)
+ InferType: 6298us [6298us] (35.30%; 35.30%)
+ FoldScaleAxis: 11541us [2us] (64.70%; 64.70%)
+ FoldConstant: 11538us [1555us] (64.68%; 99.98%)
+ InferType: 9983us [9983us] (55.97%; 86.52%)
@@ -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: 5790us [5790us] (44.67%; 44.67%)
- FoldScaleAxis: 7171us [2us] (55.33%; 55.33%)
- FoldConstant: 7169us [1501us] (55.31%; 99.98%)
- InferType: 5668us [5668us] (43.73%; 79.06%)
+ InferType: 6051us [6051us] (44.23%; 44.23%)
+ FoldScaleAxis: 7630us [2us] (55.77%; 55.77%)
+ FoldConstant: 7628us [1557us] (55.76%; 99.97%)
+ InferType: 6070us [6070us] (44.37%; 79.59%)
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 22a63ead4..ee76b269e 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: 44.960085 ms
+ Convolution: 40.847642 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 d0606f3e8..f6ee6b17c 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -628,7 +628,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 10.575889 ms
+ conv2d with tensor core: 10.216524 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 0d649eb4f..9fcdce884 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: 0.018374
- Baseline: 3.430116
+ Numpy running time: 0.018140
+ Baseline: 3.335576
@@ -210,7 +210,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.305009
+ Opt1: 0.300501
@@ -309,7 +309,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.345004
+ Opt2: 0.336995
@@ -401,7 +401,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.115727
+ Opt3: 0.115701
@@ -520,7 +520,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110674
+ Opt4: 0.110963
@@ -638,7 +638,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.112359
+ Opt5: 0.111396
@@ -759,7 +759,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145375
+ Opt6: 0.144963
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 510b61efd..e597fee47 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,8 +5,8 @@
Computation times
=================
-**00:35.286** total execution time for **how_to_optimize_operators** files:
+**00:34.767** total execution time for **how_to_optimize_operators** files:
-- **00:32.578**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
-- **00:01.470**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
-- **00:01.238**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``)
+- **00:32.101**: :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``)
+- **00:01.432**: :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``)
+- **00:01.234**: :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 67ce21888..ac86afc0c 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,11 +5,11 @@
Computation times
=================
-**05:02.483** total execution time for **how_to_tune_with_autoscheduler** files:
-
-- **02:27.689**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
-- **01:19.442**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
-- **00:40.751**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
-- **00:17.098**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
-- **00:08.908**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
-- **00:08.594**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``)
+**05:11.563** total execution time for **how_to_tune_with_autoscheduler** files:
+
+- **02:36.850**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``)
+- **01:18.838**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``)
+- **00:40.225**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``)
+- **00:18.519**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``)
+- **00:08.742**: :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``)
+- **00:08.390**: :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 869168d5f..eb883daf4 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
@@ -187,7 +187,7 @@ file and apply it.
.. code-block:: none
-
+ .T
@@ -222,333 +222,698 @@ 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, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), 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" = 16 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_2: int32 = (rc.outer.outer*196)
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- 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" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 784), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1176), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 344), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 10), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 80), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 15), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(floordiv(threadIdx.x, 49)*288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 147)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 150)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 156)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 159)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 165)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 168)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 174)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 177)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 148)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 151)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 157)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 160)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 166)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 169)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 175)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 178)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 146)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 149)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 152)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 158)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 161)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 167)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 170)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 176)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 179)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 183)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 186)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 189)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 192)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 195)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 201)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 204)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 210)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 213)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 184)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 187)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 190)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 193)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 196)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 211)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 214)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 185)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 188)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 191)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 194)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 197)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 203)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 206)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 212)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 215)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 219)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 222)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 228)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 231)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 237)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 240)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 243)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 246)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 249)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 220)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 223)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 229)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 232)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 238)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 97)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 241)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 244)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 103)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 247)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 106)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 250)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 221)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 224)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 230)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 233)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 239)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 98)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 242)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 245)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 104)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 248)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 107)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 251)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 252)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 255)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 258)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 261)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 264)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 267)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 270)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 273)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 276)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 279)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 282)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 285)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 253)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 112)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 256)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 115)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 259)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 262)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 121)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 265)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 124)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 268)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 271)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 130)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 274)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 133)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 277)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 280)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 139)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 283)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 142)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 286)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 254)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 113)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 257)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 116)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 260)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 263)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 122)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 266)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 125)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 269)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 272)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 131)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 275)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 134)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 278)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 281)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 140)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 284)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 143)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 287)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 16))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 611)]))
}
}
- for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
}
}
}
@@ -601,7 +966,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.300 ms
+ Execution time of this operator: 0.332 ms
@@ -645,36 +1010,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+ conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
- conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+ conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+ conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
- conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+ conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
- conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
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=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
- conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+ conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+ conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2 [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
- compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+ compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+ compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+ compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
- compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+ compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -694,12 +1059,12 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+ 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=16)
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=392)
+ 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=16)
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, "unroll_explicit", True)
@@ -719,320 +1084,616 @@ 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__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 120) {
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 24) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- if (((int)threadIdx.x) < 344) {
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 88) % 144))];
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((((int)threadIdx.x) < 9) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 96) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 5) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 16)];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 147)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 150)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 156)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 159)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 165)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 168)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 174)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 177)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 148)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 151)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 157)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 160)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 166)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 169)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 175)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 178)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 146)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 149)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 158)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 161)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 167)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 170)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 176)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 179)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 183)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 186)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 189)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 192)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 195)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 201)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 213)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 184)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 187)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 190)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 193)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 196)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 211)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 214)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 185)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 188)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 191)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 194)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 197)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 203)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 206)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 212)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 215)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 219)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 222)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 228)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 231)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 237)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 240)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 243)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 246)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 249)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 220)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 223)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 229)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 232)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 238)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 97)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 241)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 244)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 103)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 247)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 106)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 250)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 221)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 224)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 230)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 233)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 239)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 98)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 242)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 245)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 104)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 248)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 107)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 251)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 255)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 258)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 264)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 267)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 273)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 276)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 282)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 285)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 112)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 256)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 115)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 259)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 121)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 265)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 124)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 268)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 130)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 274)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 133)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 277)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 139)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 283)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 142)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 286)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 113)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 257)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 116)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 260)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 122)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 266)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 125)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 269)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 275)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 134)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 278)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 281)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 140)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 284)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 143)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 287)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
}
}
@@ -1091,7 +1752,7 @@ In the example below we resume the status and do more 5 trials.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 27.689 seconds)
+ **Total running time of the script:** ( 2 minutes 36.850 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 5bf314889..4368cb6c1 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -614,7 +614,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7327 9.7499 9.7608 9.6874 0.0323
+ 9.9808 9.9960 10.0422 9.9044 0.0573
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 893929ef6..409a12e10 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -633,7 +633,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 776.9521 778.1767 785.8943 766.7854 7.8491
+ 758.6640 761.3320 762.2156 752.4443 4.4127
@@ -658,7 +658,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.442 seconds)
+ **Total running time of the script:** ( 1 minutes 18.838 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 3679f5d92..7f56e9016 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
@@ -362,74 +362,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 2) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_19: int32 = (i.inner*16)
- let cse_var_18: int32 = (elem_idx*16)
- let cse_var_17: int32 = (cse_var_19 + 1)
- let cse_var_16: int32 = (cse_var_19 + 11)
- let cse_var_15: int32 = (cse_var_19 + 12)
- let cse_var_14: int32 = (cse_var_19 + 13)
- let cse_var_13: int32 = (cse_var_19 + 14)
- let cse_var_12: int32 = (cse_var_19 + 15)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 3)
- let cse_var_9: int32 = (cse_var_19 + 4)
- let cse_var_8: int32 = (cse_var_19 + 5)
- let cse_var_7: int32 = (cse_var_19 + 6)
- let cse_var_6: int32 = (cse_var_19 + 7)
- let cse_var_5: int32 = (cse_var_19 + 8)
- let cse_var_4: int32 = (cse_var_19 + 9)
- let cse_var_3: int32 = (cse_var_19 + 10)
- let cse_var_2: int32 = ((i0.outer*16384) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[i1.outer]*16) + cse_var_18)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 1)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 2)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 3)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 4)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 5)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 6)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 7)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 8)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 9)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 10)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 11)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 12)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 13)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 14)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 15)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_20: int32 = (((i0.outer*32768) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -483,7 +437,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.827 ms
+ Execution time of this operator: 1.652 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 a87274895..ebbf66a12 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:45.149** total execution time for **how_to_tune_with_autotvm** files:
+**00:44.545** total execution time for **how_to_tune_with_autotvm** files:
-- **00:44.254**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
-- **00:00.231**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
-- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_arm.py` (``tune_relay_arm.py``)
-- **00:00.221**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
-- **00:00.220**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:43.644**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``)
+- **00:00.238**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_mobile_gpu.py` (``tune_relay_mobile_gpu.py``)
+- **00:00.222**: :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``)
+- **00:00.219**: :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 2cb34eeb7..ff78d6e7c 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: 42.37/42.37 result: MeasureResult(costs=(0.005464217842105263,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6299574375152588, timestamp=1652998473.6206386) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
- No: 7 GFLOPS: 0.00/42.37 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 110.63/110.63 result: MeasureResult(costs=(0.002092602168831169,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8660893440246582, timestamp=1653006213.9576814) [('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: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/110.63 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: 0x00007f85570affa2
+ 12: 0x00007f8dd9a66fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2384,7 +2384,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.07/144.07 result: MeasureResult(costs=(0.0016068514099999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4168341159820557, timestamp=1652998500.097603) [('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: 142.66/142.66 result: MeasureResult(costs=(0.00162276938,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4110479354858398, timestamp=1653006240.4081233) [('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: 0.001991
+ Time cost of this operator: 0.002064
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 dcf1c6b28..f152381ea 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -292,10 +292,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.7 98.754 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.963 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
- Total_time - 318.671 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.1 98.745 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.966 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.289 (1, 1, 10, 10, 3) 1 1
+ Total_time - 318.092 - - - -
@@ -357,10 +357,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.65 96.794 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.1 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 1.105 (1, 1, 10, 10, 3) 1 1
- Total_time - 83.321 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 151.8 98.251 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.146 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 0.603 (1, 1, 10, 10, 3) 1 1
+ Total_time - 154.502 - - - -
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 ef9bf6d21..f272ccc13 100644
--- a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:47.288** total execution time for **how_to_work_with_microtvm** files:
+**00:46.347** total execution time for **how_to_work_with_microtvm** files:
-- **00:42.924**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
-- **00:03.743**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
-- **00:00.210**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``)
-- **00:00.209**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
-- **00:00.201**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:42.115**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``)
+- **00:03.624**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``)
+- **00:00.207**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_tvmc.py` (``micro_tvmc.py``)
+- **00:00.202**: :ref:`sphx_glr_how_to_work_with_microtvm_micro_reference_vm.py` (``micro_reference_vm.py``)
+- **00:00.199**: :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 0c68d4ce7..1f4a349e5 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
=================
-**00:11.314** total execution time for **how_to_work_with_relay** files:
+**00:09.105** total execution time for **how_to_work_with_relay** files:
-- **00:08.1000**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
-- **00:02.088**: :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``)
+- **00:07.092**: :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``)
+- **00:01.790**: :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``)
+- **00:00.224**: :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 053eff2a4..f90d00377 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
=================
-**00:05.946** total execution time for **how_to_work_with_schedules** files:
+**00:05.694** total execution time for **how_to_work_with_schedules** files:
-- **00:02.127**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
-- **00:01.321**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
-- **00:00.744**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
-- **00:00.727**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
-- **00:00.314**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
-- **00:00.248**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
-- **00:00.240**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
-- **00:00.226**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
+- **00:02.070**: :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``)
+- **00:01.161**: :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``)
+- **00:00.727**: :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``)
+- **00:00.720**: :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``)
+- **00:00.310**: :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``)
+- **00:00.245**: :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``)
+- **00:00.235**: :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``)
+- **00:00.225**: :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``)
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index bc04b30ae..e94405461 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/tmpsi5tzvuq/input0.cc'\nsource_filename = \"/tmp/tmpsi5tzvuq/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/tmp6xk27wz5/input0.cc'\nsource_filename = \"/tmp/tmp6xk27wz5/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 2e33438ca..082461a2b 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,7 +5,7 @@
Computation times
=================
-**00:20.549** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.432** total execution time for **topic_vta_tutorials_autotvm** files:
-- **00:20.337**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
-- **00:00.212**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``)
+- **00:20.227**: :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``)
+- **00:00.205**: :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 23c833e83..fea0cb4c0 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -265,7 +265,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 21.68s!
+ resnet18_v1 inference graph built in 21.28s!
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 3e7c9ca3c..ba3264bdf 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -301,7 +301,7 @@ The compilation steps are:
/workspace/python/tvm/relay/build_module.py:431: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.14s!
+ yolov3-tiny inference graph built in 14.90s!
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 e167b715d..c4519e4e8 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
=================
-**01:28.484** total execution time for **topic_vta_tutorials_frontend** files:
+**01:28.270** total execution time for **topic_vta_tutorials_frontend** files:
-- **00:46.724**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
-- **00:41.759**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``)
+- **00:46.858**: :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``)
+- **00:41.412**: :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 96892b8de..dea2ae816 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
=================
-**00:03.571** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.525** total execution time for **topic_vta_tutorials_optimize** files:
-- **00:03.011**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
-- **00:00.561**: :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``)
+- **00:02.976**: :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``)
+- **00:00.548**: :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 cfa18f7ef..822c644cb 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
=================
-**00:01.038** total execution time for **topic_vta_tutorials** files:
+**00:01.011** total execution time for **topic_vta_tutorials** files:
-- **00:00.530**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
-- **00:00.508**: :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``)
+- **00:00.512**: :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``)
+- **00:00.499**: :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 d47900a1b..42f2d6f13 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -184,7 +184,7 @@ trials, we can load the best schedule from the log file and apply it.
.. code-block:: none
- *E
+
@@ -306,7 +306,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.660 ms
+ Execution time of this operator: 93.993 ms
@@ -415,11 +415,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 15.639 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index 5428049c3..39bdaabe4 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -271,7 +271,7 @@ standard deviation.
.. code-block:: none
- {'mean': 500.2611914899944, 'median': 500.18543009999803, 'std': 0.6147697285074821}
+ {'mean': 493.5754272800006, 'median': 493.5830844000009, 'std': 0.7694217570552788}
@@ -485,31 +485,31 @@ 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: 17.39/ 17.39 GFLOPS | Progress: (4/20) | 6.17 s
[Task 1/25] Current/Best: 6.15/ 17.39 GFLOPS | Progress: (8/20) | 9.17 s
[Task 1/25] Current/Best: 11.34/ 22.71 GFLOPS | Progress: (12/20) | 11.66 s
[Task 1/25] Current/Best: 16.70/ 22.71 GFLOPS | Progress: (16/20) | 13.35 s
[Task 1/25] Current/Best: 11.59/ 23.84 GFLOPS | Progress: (20/20) | 15.09 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.20/ 12.85 GFLOPS | Progress: (4/20) | 3.92 s
[Task 2/25] Current/Best: 14.21/ 18.44 GFLOPS | Progress: (8/20) | 5.22 s
[Task 2/25] Current/Best: 21.10/ 21.10 GFLOPS | Progress: (12/20) | 6.55 s
[Task 2/25] Current/Best: 12.41/ 21.10 GFLOPS | Progress: (16/20) | 7.82 s
[Task 2/25] Current/Best: 19.55/ 21.10 GFLOPS | Progress: (20/20) | 9.47 s Done.
-
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.45 GFLOPS | Progress: (4/20) | 5.86 s
[Task 3/25] Current/Best: 15.46/ 16.86 GFLOPS | Progress: (8/20) | 7.79 s
[Task 3/25] Current/Best: 14.85/ 16.86 GFLOPS | Progress: (12/20) | 9.51 s
[Task 3/25] Current/Best: 7.19/ 23.68 GFLOPS | Progress: (16/20) | 11.42 s
[Task 3/25] Current/Best: 12.52/ 23.68 GFLOPS | Progress: (20/20) | 16.03 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.52/ 20.19 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.47/ 20.19 GFLOPS | Progress: (8/20) | 7.31 s
[Task 4/25] Current/Best: 21.06/ 21.06 GFLOPS | Progress: (12/20) | 12.30 s
[Task 4/25] Current/Best: 16.46/ 21.06 GFLOPS | Progress: (16/20) | 14.77 s
[Task 4/25] Current/Best: 13.12/ 21.06 GFLOPS | Progress: (20/20) | 16.78 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.68/ 10.23 GFLOPS | Progress: (4/20) | 2.59 s
[Task 5/25] Current/Best: 11.73/ 12.87 GFLOPS | Progress: (8/20) | 4.67 s
[Task 5/25] Current/Best: 9.78/ 17.99 GFLOPS | Progress: (12/20) | 7.79 s
[Task 5/25] Current/Best: 11.75/ 22.54 GFLOPS | Progress: (16/20) | 9.21 s
[Task 5/25] Current/Best: 11.74/ 22.54 GFLOPS | Progress: (20/20) | 11.12 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.30/ 20.75 GFLOPS | Progress: (4/20) | 4.11 s
[Task 6/25] Current/Best: 18.96/ 20.75 GFLOPS | Progress: (8/20) | 5.86 s
[Task 6/25] Current/Best: 12.89/ 20.75 GFLOPS | Progress: (12/20) | 7.83 s
[Task 6/25] Current/Best: 19.69/ 20.75 GFLOPS | Progress: (16/20) | 10.11 s
[Task 6/25] Current/Best: 3.73/ 20.75 GFLOPS | Progress: (20/20) | 12.62 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/ 12.16 GFLOPS | Progress: (4/20) | 3.65 s
[Task 7/25] Current/Best: 20.10/ 21.18 GFLOPS | Progress: (8/20) | 5.19 s
[Task 7/25] Current/Best: 15.97/ 21.18 GFLOPS | Progress: (12/20) | 7.10 s
[Task 7/25] Current/Best: 12.25/ 21.18 GFLOPS | Progress: (16/20) | 9.16 s
[Task 7/25] Current/Best: 6.39/ 21.63 GFLOPS | Progress: (20/20) | 11.62 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 10.36/ 14.42 GFLOPS | Progress: (4/20) | 2.88 s
[Task 8/25] Current/Best: 9.62/ 14.42 GFLOPS | Progress: (8/20) | 8.19 s
[Task 8/25] Current/Best: 12.96/ 14.42 GFLOPS | Progress: (12/20) | 14.86 s
[Task 8/25] Current/Best: 18.93/ 18.93 GFLOPS | Progress: (16/20) | 16.97 s
[Task 8/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 24.28 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/ 15.63 GFLOPS | Progress: (4/20) | 19.66 s
[Task 9/25] Current/Best: 23.20/ 23.20 GFLOPS | Progress: (8/20) | 21.44 s
[Task 9/25] Current/Best: 8.22/ 23.20 GFLOPS | Progress: (12/20) | 24.03 s
[Task 9/25] Current/Best: 15.12/ 23.20 GFLOPS | Progress: (16/20) | 26.85 s
[Task 9/25] Current/Best: 8.96/ 23.20 GFLOPS | Progress: (20/20) | 35.67 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.51/ 18.51 GFLOPS | Progress: (4/20) | 2.53 s
[Task 10/25] Current/Best: 15.47/ 18.51 GFLOPS | Progress: (8/20) | 4.19 s
[Task 10/25] Current/Best: 12.72/ 18.95 GFLOPS | Progress: (12/20) | 5.75 s
[Task 10/25] Current/Best: 19.11/ 20.53 GFLOPS | Progress: (16/20) | 6.86 s
[Task 10/25] Current/Best: 8.96/ 20.53 GFLOPS | Progress: (20/20
) | 8.39 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.27/ 18.03 GFLOPS | Progress: (4/20) | 3.38 s
[Task 11/25] Current/Best: 16.87/ 18.03 GFLOPS | Progress: (8/20) | 6.25 s
[Task 11/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (12/20) | 8.31 s
[Task 11/25] Current/Best: 13.29/ 21.05 GFLOPS | Progress: (16/20) | 11.33 s
[Task 11/25] Current/Best: 19.41/ 21.47 GFLOPS | Progress: (20/20) | 13.45 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.77/ 18.17 GFLOPS | Progress: (4/20) | 5.89 s
[Task 12/25] Current/Best: 5.21/ 18.17 GFLOPS | Progress: (8/20) | 9.91 s
[Task 12/25] Current/Best: 19.16/ 19.16 GFLOPS | Progress: (12/20) | 11.91 s
[Task 12/25] Current/Best: 13.37/ 19.16 GFLOPS | Progress: (16/20) | 14.92 s
[Task 12/25] Current/Best: 15.19/ 19.16 GFLOPS | Progress: (20/20) | 16.85 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.90/ 17.32 GFLOPS | Progress: (4/20) | 3.73 s
[Task 13/25] Current/Best: 16.06/ 20.82 GFLOPS | Progress: (8/20) | 6.36 s
[Task 13/25] Current/Best: 19.39/ 21.42 GFLOPS | Progress: (12/20) | 9.41 s
[Task 13/25] Current/Best: 12.19/ 21.42 GFLOPS | Progress: (16/20) | 12.86 s
[Task 13/25] Current/Best: 18.49/ 21.42 GFLOPS | Progress: (20/20) | 15.17 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.67/ 13.67 GFLOPS | Progress: (4/20) | 3.42 s
[Task 14/25] Current/Best: 6.07/ 13.67 GFLOPS | Progress: (8/20) | 5.61 s
[Task 14/25] Current/Best: 21.53/ 21.53 GFLOPS | Progress: (12/20) | 8.33 s
[Task 14/25] Current/Best: 16.58/ 21.53 GFLOPS | Progress: (16/20) | 10.22 s
[Task 14/25] Current/Best: 17.47/ 21.53 GFLOPS | Progress: (20/20) | 12.03 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.56/ 17.56 GFLOPS | Progress: (4/20) | 5.54 s
[Task 1/25] Current/Best: 6.16/ 17.56 GFLOPS | Progress: (8/20) | 8.87 s
[Task 1/25] Current/Best: 11.53/ 22.84 GFLOPS | Progress: (12/20) | 11.31 s
[Task 1/25] Current/Best: 16.61/ 22.84 GFLOPS | Progress: (16/20) | 12.99 s
[Task 1/25] Current/Best: 11.64/ 23.85 GFLOPS | Progress: (20/20) | 14.73 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.21/ 12.95 GFLOPS | Progress: (4/20) | 3.69 s
[Task 2/25] Current/Best: 14.16/ 18.85 GFLOPS | Progress: (8/20) | 5.02 s
[Task 2/25] Current/Best: 20.82/ 20.82 GFLOPS | Progress: (12/20) | 6.32 s
[Task 2/25] Current/Best: 12.34/ 20.82 GFLOPS | Progress: (16/20) | 7.58 s
[Task 2/25] Current/Best: 18.77/ 20.82 GFLOPS | Progress: (20/20) | 9.18 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/ 10.55 GFLOPS | Progress: (4/20) | 5.78 s
[Task 3/25] Current/Best: 15.59/ 16.88 GFLOPS | Progress: (8/20) | 7.69 s
[Task 3/25] Current/Best: 14.94/ 16.88 GFLOPS | Progress: (12/20) | 9.41 s
[Task 3/25] Current/Best: 7.22/ 23.80 GFLOPS | Progress: (16/20) | 11.30 s
[Task 3/25] Current/Best: 12.63/ 23.80 GFLOPS | Progress: (20/20) | 15.84 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.54/ 19.99 GFLOPS | Progress: (4/20) | 2.30 s
[Task 4/25] Current/Best: 6.71/ 19.99 GFLOPS | Progress: (8/20) | 7.08 s
[Task 4/25] Current/Best: 22.23/ 22.23 GFLOPS | Progress: (12/20) | 12.10 s
[Task 4/25] Current/Best: 17.32/ 22.23 GFLOPS | Progress: (16/20) | 14.53 s
[Task 4/25] Current/Best: 13.22/ 22.23 GFLOPS | Progress: (20/20) | 16.65 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.73/ 10.38 GFLOPS | Progress: (4/20) | 2.53 s
[Task 5/25] Current/Best: 11.72/ 12.56 GFLOPS | Progress: (8/20) | 4.58 s
[Task 5/25] Current/Best: 10.95/ 18.06 GFLOPS | Progress: (12/20) | 7.82 s
[Task 5/25] Current/Best: 11.68/ 22.56 GFLOPS | Progress: (16/20) | 9.22 s
[Task 5/25] Current/Best: 11.90/ 22.56 GFLOPS | Progress: (20/20) | 11.12 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.22/ 20.71 GFLOPS | Progress: (4/20) | 4.03 s
[Task 6/25] Current/Best: 19.04/ 20.71 GFLOPS | Progress: (8/20) | 5.77 s
[Task 6/25] Current/Best: 13.26/ 20.71 GFLOPS | Progress: (12/20) | 7.72 s
[Task 6/25] Current/Best: 19.99/ 20.71 GFLOPS | Progress: (16/20) | 9.98 s
[Task 6/25] Current/Best: 3.72/ 20.71 GFLOPS | Progress: (20/20) | 12.53 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.25/ 12.84 GFLOPS | Progress: (4/20) | 3.56 s
[Task 7/25] Current/Best: 20.29/ 20.90 GFLOPS | Progress: (8/20) | 5.06 s
[Task 7/25] Current/Best: 14.84/ 20.90 GFLOPS | Progress: (12/20) | 6.99 s
[Task 7/25] Current/Best: 12.23/ 20.90 GFLOPS | Progress: (16/20) | 9.03 s
[Task 7/25] Current/Best: 6.38/ 21.87 GFLOPS | Progress: (20/20) | 11.49 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.68/ 13.85 GFLOPS | Progress: (4/20) | 2.85 s
[Task 8/25] Current/Best: 9.16/ 13.85 GFLOPS | Progress: (8/20) | 8.10 s
[Task 8/25] Current/Best: 13.08/ 13.85 GFLOPS | Progress: (12/20) | 14.67 s
[Task 8/25] Current/Best: 18.90/ 18.90 GFLOPS | Progress: (16/20) | 16.76 s
[Task 8/25] Current/Best: 19.40/ 19.40 GFLOPS | Progress: (20/20) | 23.93 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.79 GFLOPS | Progress: (4/20) | 19.30 s
[Task 9/25] Current/Best: 23.48/ 23.48 GFLOPS | Progress: (8/20) | 20.99 s
[Task 9/25] Current/Best: 8.26/ 23.48 GFLOPS | Progress: (12/20) | 23.52 s
[Task 9/25] Current/Best: 18.01/ 23.48 GFLOPS | Progress: (16/20) | 26.39 s
[Task 9/25] Current/Best: 9.02/ 23.48 GFLOPS | Progress: (20/20) | 35.14 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.35/ 18.35 GFLOPS | Progress: (4/20) | 2.47 s
[Task 10/25] Current/Best: 15.28/ 18.35 GFLOPS | Progress: (8/20) | 4.12 s
[Task 10/25] Current/Best: 12.83/ 18.58 GFLOPS | Progress: (12/20) | 5.67 s
[Task 10/25] Current/Best: 19.11/ 20.27 GFLOPS | Progress: (16/20) | 6.77 s
[Task 10/25] Current/Best: 8.87/ 20.27 GFLOPS | Progress: (20/20
) | 8.30 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.24/ 18.08 GFLOPS | Progress: (4/20) | 3.28 s
[Task 11/25] Current/Best: 16.85/ 18.08 GFLOPS | Progress: (8/20) | 6.10 s
[Task 11/25] Current/Best: 18.19/ 18.19 GFLOPS | Progress: (12/20) | 8.18 s
[Task 11/25] Current/Best: 13.42/ 21.22 GFLOPS | Progress: (16/20) | 11.12 s
[Task 11/25] Current/Best: 19.45/ 21.22 GFLOPS | Progress: (20/20) | 13.20 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) | 5.72 s
[Task 12/25] Current/Best: 5.20/ 18.02 GFLOPS | Progress: (8/20) | 9.68 s
[Task 12/25] Current/Best: 19.13/ 19.13 GFLOPS | Progress: (12/20) | 11.67 s
[Task 12/25] Current/Best: 15.32/ 19.13 GFLOPS | Progress: (16/20) | 14.61 s
[Task 12/25] Current/Best: 15.13/ 19.13 GFLOPS | Progress: (20/20) | 16.52 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.69/ 17.28 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 15.02/ 21.03 GFLOPS | Progress: (8/20) | 6.28 s
[Task 13/25] Current/Best: 19.59/ 21.29 GFLOPS | Progress: (12/20) | 9.31 s
[Task 13/25] Current/Best: 12.28/ 21.29 GFLOPS | Progress: (16/20) | 12.76 s
[Task 13/25] Current/Best: 18.76/ 21.29 GFLOPS | Progress: (20/20) | 15.08 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.55/ 13.55 GFLOPS | Progress: (4/20) | 3.33 s
[Task 14/25] Current/Best: 6.00/ 13.55 GFLOPS | Progress: (8/20) | 5.52 s
[Task 14/25] Current/Best: 20.51/ 20.51 GFLOPS | Progress: (12/20) | 8.19 s
[Task 14/25] Current/Best: 16.53/ 20.51 GFLOPS | Progress: (16/20) | 10.10 s
[Task 14/25] Current/Best: 16.76/ 20.51 GFLOPS | Progress: (20/20) | 11.88 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s Done.
Done.
-
[Task 15/25] Current/Best: 16.10/ 17.56 GFLOPS | Progress: (4/20) | 2.68 s
[Task 15/25] Current/Best: 14.33/ 17.91 GFLOPS | Progress: (8/20) | 4.24 s
[Task 15/25] Current/Best: 10.34/ 22.24 GFLOPS | Progress: (12/20) | 6.64 s
[Task 15/25] Current/Best: 20.27/ 22.24 GFLOPS | Progress: (16/20) | 9.93 s
[Task 15/25] Current/Best: 9.67/ 22.24 GFLOPS | Progress: (20/20) | 11.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.62/ 20.62 GFLOPS | Progress: (4/20) | 2.90 s
[Task 16/25] Current/Best: 3.04/ 20.62 GFLOPS | Progress: (8/20) | 4.52 s
[Task 16/25] Current/Best: 19.53/ 20.62 GFLOPS | Progress: (12/20) | 5.74 s
[Task 16/25] Current/Best: 17.69/ 20.62 GFLOPS | Progress: (16/20) | 7.11 s
[Task 16/25] Current/Best: 10.03/ 21.65 GFLOPS | Progress: (20/20) | 9.33 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 14.20/ 18.85 GFLOPS | Progress: (4/20) | 4.77 s
[Task 17/25] Current/Best: 14.46/ 22.98 GFLOPS | Progress: (8/20) | 7.72 s
[Task 17/25] Current/Best: 16.72/ 22.98 GFLOPS | Progress: (12/20) | 9.79 s
[Task 17/25] Current/Best: 16.46/ 22.98 GFLOPS | Progress: (16/20) | 12.02 s
[Task 17/25] Current/Best: 10.01/ 22.98 GFLOPS | Progress: (20/20) | 14.19 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.35/ 17.84 GFLOPS | Progress: (4/20) | 3.82 s
[Task 18/25] Current/Best: 10.59/ 19.68 GFLOPS | Progress: (8/20) | 7.62 s
[Task 18/25] Current/Best: 18.74/ 19.68 GFLOPS | Progress: (12/20) | 9.58 s
[Task 18/25] Current/Best: 9.83/ 19.68 GFLOPS | Progress: (16/20) | 13.50 s
[Task 18/25] Current/Best: 20.74/ 20.74 GFLOPS | Progress: (20/20) | 15.03 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.18/ 20.10 GFLOPS | Progress: (4/20) | 6.35 s
[Task 19/25] Current/Best: 2.60/ 20.10 GFLOPS | Progress: (8/20) | 9.70 s
[Task 19/25] Current/Best: 19.31/ 20.61 GFLOPS | Progress: (12/20) | 12.69 s
[Task 19/25] Current/Best: 15.23/ 21.05 GFLOPS | Progress: (16/20) | 15.74 s
[Task 19/25] Current/Best: 2.70/ 22.95 GFLOPS | Progress: (20/20) | 18.54 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.78/ 14.89 GFLOPS | Progress: (4/20) | 3.40 s
[Task 20/25] Current/Best: 10.30/ 14.89 GFLOPS | Progress: (8/20) | 7.00 s
[Task 20/25] Current/Best: 2.33/ 16.62 GFLOPS | Progress: (12/20) | 11.00 s Done.
-
[Task 20/25] Current/Best: 12.40/ 16.62 GFLOPS | Progress: (16/20) | 14.86 s
[Task 20/25] Current/Best: 13.32/ 21.45 GFLOPS | Progress: (20/20) | 16.98 s Done.
-
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.55 GFLOPS | Progress: (4/20) | 3.28 s
[Task 21/25] Current/Best: 14.36/ 17.55 GFLOPS | Progress: (8/20) | 4.92 s
[Task 21/25] Current/Best: 1.61/ 17.55 GFLOPS | Progress: (12/20) | 7.10 s
[Task 21/25] Current/Best: 18.21/ 18.21 GFLOPS | Progress: (16/20) | 10.65 s
[Task 21/25] Current/Best: 4.45/ 18.21 GFLOPS | Progress: (20/20) | 18.18 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.93 GFLOPS | Progress: (4/20) | 2.67 s
[Task 22/25] Current/Best: 9.15/ 21.54 GFLOPS | Progress: (8/20) | 4.71 s
[Task 22/25] Current/Best: 19.61/ 21.54 GFLOPS | Progress: (12/20) | 7.11 s
[Task 22/25] Current/Best: 15.04/ 21.54 GFLOPS | Progress: (16/20) | 9.27 s
[Task 22/25] Current/Best: 14.50/ 21.54 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: 17.28/ 20.08 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 15.73/ 20.08 GFLOPS | Progress: (8/20) | 6.59 s
[Task 23/25] Current/Best: 20.58/ 21.14 GFLOPS | Progress: (12/20) | 8.47 s
[Task 23/25] Current/Best: 5.84/ 21.14 GFLOPS | Progress: (16/20) | 15.85 s
[Task 23/25] Current/Best: 7.45/ 21.14 GFLOPS | Progress: (20/20) | 20.16 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.51/ 8.51 GFLOPS | Progress: (4/20) | 14.19 s
[Task 24/25] Current/Best: 1.99/ 8.51 GFLOPS | Progress: (8/20) | 31.60 s
[Task 24/25] Current/Best: 4.23/ 8.51 GFLOPS | Progress: (12/20) | 57.06 s
[Task 24/25] Current/Best: 7.27/ 8.60 GFLOPS | Progress: (16/20) | 62.91 s Done.
-
[Task 24/25] Current/Best: 3.21/ 8.99 GFLOPS | Progress: (20/20) | 69.20 s Done.
-
[Task 25/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 25/25] Current/Best: 1.53/ 2.86 GFLOPS | Progress: (4/20) | 30.38 s
[Task 25/25] Current/Best: 5.46/ 7.59 GFLOPS | Progress: (8/20) | 358.34 s
[Task 25/25] Current/Best: 5.90/ 7.59 GFLOPS | Progress: (12/20) | 387.85 s
[Task 25/25] Current/Best: 5.73/ 9.38 GFLOPS | Progress: (16/20) | 389.79 s
[Task 25/25] Current/Best: 2.92/ 9.38 GFLOPS | Progress: (20/20) | 410.87 s
+
[Task 15/25] Current/Best: 16.18/ 17.64 GFLOPS | Progress: (4/20) | 2.60 s
[Task 15/25] Current/Best: 14.44/ 17.98 GFLOPS | Progress: (8/20) | 4.12 s
[Task 15/25] Current/Best: 10.41/ 22.27 GFLOPS | Progress: (12/20) | 6.45 s
[Task 15/25] Current/Best: 20.39/ 22.27 GFLOPS | Progress: (16/20) | 9.46 s
[Task 15/25] Current/Best: 9.71/ 22.27 GFLOPS | Progress: (20/20) | 10.61 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 19.54/ 19.54 GFLOPS | Progress: (4/20) | 2.91 s
[Task 16/25] Current/Best: 3.02/ 19.54 GFLOPS | Progress: (8/20) | 4.51 s
[Task 16/25] Current/Best: 19.11/ 19.54 GFLOPS | Progress: (12/20) | 5.71 s
[Task 16/25] Current/Best: 17.92/ 19.54 GFLOPS | Progress: (16/20) | 7.11 s
[Task 16/25] Current/Best: 9.98/ 20.43 GFLOPS | Progress: (20/20) | 9.28 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.20/ 18.82 GFLOPS | Progress: (4/20) | 4.71 s
[Task 17/25] Current/Best: 13.59/ 23.33 GFLOPS | Progress: (8/20) | 7.62 s
[Task 17/25] Current/Best: 16.93/ 23.33 GFLOPS | Progress: (12/20) | 9.65 s
[Task 17/25] Current/Best: 16.55/ 23.33 GFLOPS | Progress: (16/20) | 11.90 s
[Task 17/25] Current/Best: 10.05/ 23.33 GFLOPS | Progress: (20/20) | 14.04 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.15/ 17.60 GFLOPS | Progress: (4/20) | 3.75 s
[Task 18/25] Current/Best: 10.62/ 18.75 GFLOPS | Progress: (8/20) | 7.47 s
[Task 18/25] Current/Best: 18.62/ 18.75 GFLOPS | Progress: (12/20) | 9.41 s
[Task 18/25] Current/Best: 9.97/ 18.75 GFLOPS | Progress: (16/20) | 13.33 s
[Task 18/25] Current/Best: 20.43/ 20.43 GFLOPS | Progress: (20/20) | 14.87 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.09/ 20.36 GFLOPS | Progress: (4/20) | 6.02 s
[Task 19/25] Current/Best: 2.60/ 20.36 GFLOPS | Progress: (8/20) | 9.36 s
[Task 19/25] Current/Best: 20.17/ 21.80 GFLOPS | Progress: (12/20) | 12.35 s
[Task 19/25] Current/Best: 15.46/ 21.80 GFLOPS | Progress: (16/20) | 15.33 s
[Task 19/25] Current/Best: 2.70/ 23.28 GFLOPS | Progress: (20/20) | 18.21 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.57/ 14.96 GFLOPS | Progress: (4/20) | 3.28 s
[Task 20/25] Current/Best: 10.63/ 14.96 GFLOPS | Progress: (8/20) | 6.77 s
[Task 20/25] Current/Best: 2.32/ 16.58 GFLOPS | Progress: (12/20) | 10.64 s Done.
+
[Task 20/25] Current/Best: 12.31/ 16.58 GFLOPS | Progress: (16/20) | 14.62 s
[Task 20/25] Current/Best: 13.24/ 22.21 GFLOPS | Progress: (20/20) | 16.71 s Done.
+
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.40/ 17.68 GFLOPS | Progress: (4/20) | 3.22 s
[Task 21/25] Current/Best: 14.60/ 17.68 GFLOPS | Progress: (8/20) | 4.81 s
[Task 21/25] Current/Best: 1.61/ 17.68 GFLOPS | Progress: (12/20) | 6.93 s
[Task 21/25] Current/Best: 18.12/ 18.12 GFLOPS | Progress: (16/20) | 10.44 s
[Task 21/25] Current/Best: 4.46/ 18.12 GFLOPS | Progress: (20/20) | 17.86 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.01 GFLOPS | Progress: (4/20) | 2.61 s
[Task 22/25] Current/Best: 8.58/ 21.36 GFLOPS | Progress: (8/20) | 4.66 s
[Task 22/25] Current/Best: 19.98/ 21.36 GFLOPS | Progress: (12/20) | 7.08 s
[Task 22/25] Current/Best: 15.26/ 21.36 GFLOPS | Progress: (16/20) | 9.20 s
[Task 22/25] Current/Best: 14.39/ 21.36 GFLOPS | Progress: (20/20) |
10.88 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.56/ 20.52 GFLOPS | Progress: (4/20) | 3.19 s
[Task 23/25] Current/Best: 14.63/ 20.52 GFLOPS | Progress: (8/20) | 6.57 s
[Task 23/25] Current/Best: 20.95/ 21.77 GFLOPS | Progress: (12/20) | 8.41 s
[Task 23/25] Current/Best: 6.30/ 21.77 GFLOPS | Progress: (16/20) | 15.36 s
[Task 23/25] Current/Best: 7.86/ 21.77 GFLOPS | Progress: (20/20) | 19.58 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.32/ 8.32 GFLOPS | Progress: (4/20) | 13.90 s
[Task 24/25] Current/Best: 3.63/ 8.32 GFLOPS | Progress: (8/20) | 29.96 s
[Task 24/25] Current/Best: 4.34/ 8.32 GFLOPS | Progress: (12/20) | 53.94 s
[Task 24/25] Current/Best: 7.29/ 8.78 GFLOPS | Progress: (16/20) | 59.62 s Done.
+
[Task 24/25] Current/Best: 3.28/ 8.80 GFLOPS | Progress: (20/20) | 65.80 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/ 2.83 GFLOPS | Progress: (4/20) | 32.30 s
[Task 25/25] Current/Best: 5.87/ 7.91 GFLOPS | Progress: (8/20) | 326.73 s
[Task 25/25] Current/Best: 5.88/ 7.91 GFLOPS | Progress: (12/20) | 354.84 s
[Task 25/25] Current/Best: 5.73/ 9.21 GFLOPS | Progress: (16/20) | 356.57 s
[Task 25/25] Current/Best: 2.88/ 9.21 GFLOPS | Progress: (20/20) | 376.50 s
The output from this tuning process will look something like this:
@@ -651,8 +651,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 415.859262619997, 'median': 415.70024575000843, 'std': 0.7134304350709059}
- unoptimized: {'mean': 500.2611914899944, 'median': 500.18543009999803, 'std': 0.6147697285074821}
+ optimized: {'mean': 412.3051284600001, 'median': 412.33388544999343, 'std': 0.6682924602970655}
+ unoptimized: {'mean': 493.5754272800006, 'median': 493.5830844000009, 'std': 0.7694217570552788}
@@ -672,7 +672,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 17 minutes 7.751 seconds)
+ **Total running time of the script:** ( 16 minutes 19.943 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 fae3792ae..4347fee4c 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
- 1.312e-07 secs/op
+ 1.281e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 275c99c09..ac4c0c507 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -233,7 +233,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x4d8ccf0)), stage(b, placeholder(b, 0x21166eb0)), 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, 0x150a5a50)), stage(b, placeholder(b, 0xcf05f40)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index c1cee5146..9c25a8f89 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
=================
-**20:19.304** total execution time for **tutorial** files:
+**19:08.111** total execution time for **tutorial** files:
-- **17:07.751**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
-- **01:15.639**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
-- **01:02.531**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
-- **00:26.649**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
-- **00:24.248**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
-- **00:01.302**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
-- **00:00.735**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
-- **00:00.234**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
-- **00:00.054**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
+- **16:19.943**: :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``)
+- **00:59.975**: :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``)
+- **00:53.114**: :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``)
+- **00:26.610**: :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``)
+- **00:26.095**: :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``)
+- **00:01.297**: :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``)
+- **00:00.713**: :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``)
+- **00:00.207**: :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``)
+- **00:00.045**: :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``)
+- **00:00.043**: :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``)
+- **00:00.036**: :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``)
+- **00:00.032**: :ref:`sphx_glr_tutorial_install.py` (``install.py``)
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index c006d4e72..9fb7456c7 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -243,8 +243,8 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000009
- naive: 0.000008
+ Numpy running time: 0.000007
+ naive: 0.000006
@@ -335,7 +335,7 @@ compile and run this new schedule with the parallel operation applied:
.. code-block:: none
- parallel: 0.000007
+ parallel: 0.000006
@@ -438,10 +438,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 9.0214100009689e-06 1.0
- naive 7.593499999999999e-06 0.8417198640993434
- parallel 7.101200000000001e-06 0.7871496805086269
- vector 2.46336e-05 2.7305709414996495
+ numpy 6.94634999945265e-06 1.0
+ naive 5.861299999999999e-06 0.8437956625367065
+ parallel 6.0771e-06 0.874862337843451
+ vector 2.4575600000000002e-05 3.537915596239245
@@ -830,7 +830,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.019410
+ Numpy running time: 0.018190
@@ -886,7 +886,7 @@ optimizations.
.. code-block:: none
- none: 3.472838
+ none: 3.339995
@@ -985,7 +985,7 @@ schedule.
.. code-block:: none
- blocking: 0.330106
+ blocking: 0.302982
@@ -1077,7 +1077,7 @@ already cache friendly from our previous optimizations.
.. code-block:: none
- vectorization: 0.346800
+ vectorization: 0.338120
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1149,7 +1149,7 @@ more cache friendly.
.. code-block:: none
- loop permutation: 0.129790
+ loop permutation: 0.117253
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1246,7 +1246,7 @@ optimized schedule.
.. code-block:: none
- array packing: 0.110359
+ array packing: 0.110143
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1337,7 +1337,7 @@ to `C` when all the block results are ready.
.. code-block:: none
- block caching: 0.112097
+ block caching: 0.110539
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1421,7 +1421,7 @@ of thread-level parallelization.
.. code-block:: none
- parallelization: 0.146660
+ parallelization: 0.144205
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1500,13 +1500,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4728383816000004 1.0
- blocking 0.33010644990000004 0.09505378990539547
- vectorization 0.34679975209999997 0.09986060795038293
- loop permutation 0.1297897168 0.03737280648810484
- array packing 0.11035858579999999 0.03177763364535143
- block caching 0.11209719199999998 0.03227826339224999
- parallelization 0.1466603206 0.042230678334196164
+ none 3.3399949796999997 1.0
+ blocking 0.3029824418 0.09071344227805218
+ vectorization 0.338119565 0.10123355485713038
+ loop permutation 0.11725255790000003 0.035105609024158387
+ array packing 0.1101429562 0.032976982561181305
+ block caching 0.11053856209999999 0.03309542761945367
+ parallelization 0.1442045778 0.0431750881891902
@@ -1541,11 +1541,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 2.531 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
diff --git a/docs/commit_hash b/docs/commit_hash
index 684691489..5cdd9a618 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-cd269101b7c508f5432ad4aee3c1ff8d07a89142
+5e29dddd02193a440c18a1d98fef9023cb008788
diff --git a/docs/genindex.html b/docs/genindex.html
index 124985333..dedcfa743 100644
--- a/docs/genindex.html
+++ b/docs/genindex.html
@@ -447,6 +447,8 @@
<li><a href="reference/api/python/auto_scheduler.html#tvm.auto_scheduler.ComputeDAG.apply_steps_from_state">apply_steps_from_state() (tvm.auto_scheduler.ComputeDAG method)</a>
</li>
<li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyConfig">ApplyConfig (class in tvm.autotvm.task.dispatcher)</a>
+</li>
+ <li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyFixedConfig">ApplyFixedConfig (class in tvm.autotvm.task.dispatcher)</a>
</li>
<li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyGraphBest">ApplyGraphBest (class in tvm.autotvm.task.dispatcher)</a>
</li>
@@ -4428,6 +4430,8 @@
<li><a href="reference/api/python/auto_scheduler.html#tvm.auto_scheduler.XGBModel.update">(tvm.auto_scheduler.XGBModel method)</a>
</li>
<li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyConfig.update">(tvm.autotvm.task.dispatcher.ApplyConfig method)</a>
+</li>
+ <li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyFixedConfig.update">(tvm.autotvm.task.dispatcher.ApplyFixedConfig method)</a>
</li>
<li><a href="reference/api/python/autotvm.html#tvm.autotvm.task.dispatcher.ApplyGraphBest.update">(tvm.autotvm.task.dispatcher.ApplyGraphBest method)</a>
</li>
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index bc092c7fa..67c842ac7 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.zip69bf84d8-fe7f-42be-9dc6-2d49679d54ab 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.zip9bbde507-bb5f-467a-81f5-ff1cb26580ad 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 5593bbac2..266d6992b 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -406,43 +406,727 @@ 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<07:43, 93.9kB/s]
- 0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
- 0%| | 96.0k/41.5M [00:00<03:28, 209kB/s]
- 0%| | 160k/41.5M [00:00<02:38, 274kB/s]
- 1%| | 296k/41.5M [00:00<01:33, 461kB/s]
- 1%|1 | 608k/41.5M [00:01<00:46, 923kB/s]
- 3%|2 | 1.08M/41.5M [00:01<00:27, 1.57MB/s]
- 5%|5 | 2.10M/41.5M [00:01<00:13, 3.01MB/s]
- 9%|8 | 3.61M/41.5M [00:01<00:08, 4.89MB/s]
- 12%|#2 | 5.11M/41.5M [00:01<00:06, 6.14MB/s]
- 16%|#5 | 6.62M/41.5M [00:01<00:05, 7.02MB/s]
- 20%|#9 | 8.12M/41.5M [00:02<00:04, 7.62MB/s]
- 23%|##3 | 9.62M/41.5M [00:02<00:04, 8.01MB/s]
- 27%|##6 | 11.1M/41.5M [00:02<00:03, 8.31MB/s]
- 30%|### | 12.6M/41.5M [00:02<00:03, 8.49MB/s]
- 34%|###4 | 14.1M/41.5M [00:02<00:03, 8.65MB/s]
- 38%|###7 | 15.6M/41.5M [00:02<00:03, 8.74MB/s]
- 41%|####1 | 17.1M/41.5M [00:03<00:02, 8.82MB/s]
- 45%|####4 | 18.6M/41.5M [00:03<00:02, 8.85MB/s]
- 49%|####8 | 20.1M/41.5M [00:03<00:02, 8.89MB/s]
- 52%|#####2 | 21.6M/41.5M [00:03<00:02, 8.87MB/s]
- 56%|#####5 | 23.1M/41.5M [00:03<00:02, 8.91MB/s]
- 59%|#####9 | 24.6M/41.5M [00:04<00:01, 8.93MB/s]
- 63%|######2 | 26.1M/41.5M [00:04<00:01, 8.95MB/s]
- 67%|######6 | 27.6M/41.5M [00:04<00:01, 10.0MB/s]
- 70%|####### | 29.1M/41.5M [00:04<00:01, 10.5MB/s]
- 73%|#######2 | 30.1M/41.5M [00:04<00:01, 10.1MB/s]
- 75%|#######4 | 31.1M/41.5M [00:04<00:01, 8.74MB/s]
- 77%|#######7 | 32.1M/41.5M [00:04<00:01, 8.28MB/s]
- 81%|######## | 33.6M/41.5M [00:05<00:00, 9.24MB/s]
- 83%|########3 | 34.5M/41.5M [00:05<00:01, 6.91MB/s]
- 85%|########4 | 35.2M/41.5M [00:05<00:01, 6.21MB/s]
- 88%|########8 | 36.7M/41.5M [00:05<00:00, 6.96MB/s]
- 92%|#########2| 38.2M/41.5M [00:05<00:00, 7.57MB/s]
- 96%|#########5| 39.7M/41.5M [00:05<00:00, 8.01MB/s]
- 99%|#########9| 41.2M/41.5M [00:06<00:00, 8.29MB/s]
-100%|##########| 41.5M/41.5M [00:06<00:00, 7.07MB/s]
+ 0%| | 16.0k/41.5M [00:00<22:35, 32.1kB/s]
+ 0%| | 32.0k/41.5M [00:00<15:57, 45.4kB/s]
+ 0%| | 48.0k/41.5M [00:01<13:50, 52.4kB/s]
+ 0%| | 56.0k/41.5M [00:01<21:34, 33.6kB/s]
+ 0%| | 64.0k/41.5M [00:01<21:51, 33.1kB/s]
+ 0%| | 80.0k/41.5M [00:02<17:21, 41.7kB/s]
+ 0%| | 96.0k/41.5M [00:02<19:19, 37.4kB/s]
+ 0%| | 104k/41.5M [00:03<24:49, 29.1kB/s]
+ 0%| | 112k/41.5M [00:03<29:34, 24.5kB/s]
+ 0%| | 128k/41.5M [00:04<32:03, 22.6kB/s]
+ 0%| | 136k/41.5M [00:05<50:05, 14.4kB/s]
+ 0%| | 144k/41.5M [00:07<1:25:02, 8.50kB/s]
+ 0%| | 152k/41.5M [00:08<1:20:35, 8.97kB/s]
+ 0%| | 160k/41.5M [00:09<1:17:06, 9.37kB/s]
+ 0%| | 168k/41.5M [00:09<1:08:13, 10.6kB/s]
+ 0%| | 176k/41.5M [00:10<55:17, 13.1kB/s]
+ 0%| | 184k/41.5M [00:13<1:51:54, 6.45kB/s]
+ 0%| | 192k/41.5M [00:14<1:44:10, 6.93kB/s]
+ 0%| | 200k/41.5M [00:14<1:21:31, 8.85kB/s]
+ 0%| | 208k/41.5M [00:15<1:22:40, 8.73kB/s]
+ 1%| | 216k/41.5M [00:15<1:11:29, 10.1kB/s]
+ 1%| | 224k/41.5M [00:16<1:03:36, 11.3kB/s]
+ 1%| | 232k/41.5M [00:17<1:11:31, 10.1kB/s]
+ 1%| | 240k/41.5M [00:17<56:51, 12.7kB/s]
+ 1%| | 248k/41.5M [00:18<53:17, 13.5kB/s]
+ 1%| | 256k/41.5M [00:20<1:35:07, 7.58kB/s]
+ 1%| | 264k/41.5M [00:20<1:13:21, 9.82kB/s]
+ 1%| | 272k/41.5M [00:20<58:06, 12.4kB/s]
+ 1%| | 280k/41.5M [00:21<47:26, 15.2kB/s]
+ 1%| | 288k/41.5M [00:21<51:59, 13.8kB/s]
+ 1%| | 304k/41.5M [00:22<44:37, 16.1kB/s]
+ 1%| | 320k/41.5M [00:22<31:22, 22.9kB/s]
+ 1%| | 328k/41.5M [00:23<29:25, 24.5kB/s]
+ 1%| | 336k/41.5M [00:23<37:21, 19.3kB/s]
+ 1%| | 344k/41.5M [00:24<34:47, 20.7kB/s]
+ 1%| | 352k/41.5M [00:24<42:26, 16.9kB/s]
+ 1%| | 360k/41.5M [00:25<43:05, 16.7kB/s]
+ 1%| | 368k/41.5M [00:25<37:34, 19.1kB/s]
+ 1%| | 376k/41.5M [00:26<35:57, 20.0kB/s]
+ 1%| | 384k/41.5M [00:26<30:08, 23.8kB/s]
+ 1%| | 392k/41.5M [00:26<30:40, 23.4kB/s]
+ 1%| | 400k/41.5M [00:26<26:19, 27.3kB/s]
+ 1%| | 408k/41.5M [00:26<23:14, 30.9kB/s]
+ 1%| | 416k/41.5M [00:27<21:05, 34.1kB/s]
+ 1%|1 | 432k/41.5M [00:27<15:03, 47.6kB/s]
+ 1%|1 | 440k/41.5M [00:27<15:16, 47.0kB/s]
+ 1%|1 | 448k/41.5M [00:27<15:27, 46.4kB/s]
+ 1%|1 | 464k/41.5M [00:27<12:15, 58.5kB/s]
+ 1%|1 | 472k/41.5M [00:28<13:07, 54.6kB/s]
+ 1%|1 | 480k/41.5M [00:28<13:49, 51.8kB/s]
+ 1%|1 | 496k/41.5M [00:28<11:22, 63.0kB/s]
+ 1%|1 | 512k/41.5M [00:28<10:06, 70.9kB/s]
+ 1%|1 | 520k/41.5M [00:28<11:19, 63.2kB/s]
+ 1%|1 | 536k/41.5M [00:28<10:03, 71.1kB/s]
+ 1%|1 | 552k/41.5M [00:29<09:19, 76.7kB/s]
+ 1%|1 | 568k/41.5M [00:29<08:52, 80.6kB/s]
+ 1%|1 | 584k/41.5M [00:29<08:34, 83.4kB/s]
+ 1%|1 | 600k/41.5M [00:29<08:23, 85.2kB/s]
+ 1%|1 | 624k/41.5M [00:29<07:08, 100kB/s]
+ 2%|1 | 640k/41.5M [00:30<07:21, 97.0kB/s]
+ 2%|1 | 664k/41.5M [00:30<06:35, 108kB/s]
+ 2%|1 | 696k/41.5M [00:30<05:29, 130kB/s]
+ 2%|1 | 728k/41.5M [00:30<04:55, 145kB/s]
+ 2%|1 | 760k/41.5M [00:30<04:35, 155kB/s]
+ 2%|1 | 800k/41.5M [00:30<04:02, 176kB/s]
+ 2%|1 | 840k/41.5M [00:31<03:43, 191kB/s]
+ 2%|2 | 888k/41.5M [00:31<03:18, 214kB/s]
+ 2%|2 | 944k/41.5M [00:31<02:54, 244kB/s]
+ 2%|2 | 0.98M/41.5M [00:31<02:45, 256kB/s]
+ 3%|2 | 1.04M/41.5M [00:31<02:44, 258kB/s]
+ 3%|2 | 1.11M/41.5M [00:32<02:37, 268kB/s]
+ 3%|2 | 1.14M/41.5M [00:32<05:16, 134kB/s]
+ 3%|3 | 1.27M/41.5M [00:34<05:54, 119kB/s]
+ 3%|3 | 1.39M/41.5M [00:34<04:06, 171kB/s]
+ 3%|3 | 1.42M/41.5M [00:34<04:16, 164kB/s]
+ 3%|3 | 1.45M/41.5M [00:35<04:39, 150kB/s]
+ 4%|3 | 1.48M/41.5M [00:35<05:51, 120kB/s]
+ 4%|3 | 1.50M/41.5M [00:36<08:34, 81.5kB/s]
+ 4%|3 | 1.54M/41.5M [00:36<07:20, 95.0kB/s]
+ 4%|3 | 1.55M/41.5M [00:36<08:12, 85.1kB/s]
+ 4%|3 | 1.57M/41.5M [00:38<17:24, 40.1kB/s]
+ 4%|3 | 1.59M/41.5M [00:40<32:07, 21.7kB/s]
+ 4%|3 | 1.59M/41.5M [00:41<33:30, 20.8kB/s]
+ 4%|3 | 1.60M/41.5M [00:42<52:56, 13.2kB/s]
+ 4%|3 | 1.61M/41.5M [00:43<51:16, 13.6kB/s]
+ 4%|3 | 1.62M/41.5M [00:43<45:22, 15.4kB/s]
+ 4%|3 | 1.62M/41.5M [00:43<40:07, 17.4kB/s]
+ 4%|3 | 1.63M/41.5M [00:44<35:41, 19.5kB/s]
+ 4%|3 | 1.64M/41.5M [00:44<32:07, 21.7kB/s]
+ 4%|3 | 1.66M/41.5M [00:44<23:09, 30.1kB/s]
+ 4%|4 | 1.66M/41.5M [00:45<32:52, 21.2kB/s]
+ 4%|4 | 1.68M/41.5M [00:46<37:05, 18.8kB/s]
+ 4%|4 | 1.70M/41.5M [00:48<46:25, 15.0kB/s]
+ 4%|4 | 1.70M/41.5M [00:49<59:12, 11.7kB/s]
+ 4%|4 | 1.71M/41.5M [00:50<1:05:27, 10.6kB/s]
+ 4%|4 | 1.72M/41.5M [00:50<54:42, 12.7kB/s]
+ 4%|4 | 1.73M/41.5M [00:51<51:45, 13.4kB/s]
+ 4%|4 | 1.73M/41.5M [00:51<43:37, 15.9kB/s]
+ 4%|4 | 1.74M/41.5M [00:51<37:30, 18.5kB/s]
+ 4%|4 | 1.75M/41.5M [00:53<1:02:31, 11.1kB/s]
+ 4%|4 | 1.77M/41.5M [00:53<45:13, 15.4kB/s]
+ 4%|4 | 1.77M/41.5M [00:54<47:44, 14.5kB/s]
+ 4%|4 | 1.78M/41.5M [00:55<53:21, 13.0kB/s]
+ 4%|4 | 1.80M/41.5M [00:55<39:54, 17.4kB/s]
+ 4%|4 | 1.80M/41.5M [00:56<40:41, 17.0kB/s]
+ 4%|4 | 1.81M/41.5M [00:56<35:55, 19.3kB/s]
+ 4%|4 | 1.82M/41.5M [00:56<37:49, 18.3kB/s]
+ 4%|4 | 1.83M/41.5M [00:57<39:16, 17.6kB/s]
+ 4%|4 | 1.84M/41.5M [00:57<40:23, 17.2kB/s]
+ 4%|4 | 1.84M/41.5M [00:58<35:02, 19.8kB/s]
+ 4%|4 | 1.85M/41.5M [00:59<49:56, 13.9kB/s]
+ 5%|4 | 1.87M/41.5M [01:01<1:13:07, 9.47kB/s]
+ 5%|4 | 1.88M/41.5M [01:02<1:14:05, 9.34kB/s]
+ 5%|4 | 1.88M/41.5M [01:02<1:02:51, 11.0kB/s]
+ 5%|4 | 1.89M/41.5M [01:03<50:02, 13.8kB/s]
+ 5%|4 | 1.90M/41.5M [01:03<44:40, 15.5kB/s]
+ 5%|4 | 1.91M/41.5M [01:03<36:20, 19.0kB/s]
+ 5%|4 | 1.91M/41.5M [01:03<30:16, 22.8kB/s]
+ 5%|4 | 1.92M/41.5M [01:03<25:55, 26.7kB/s]
+ 5%|4 | 1.93M/41.5M [01:04<22:49, 30.3kB/s]
+ 5%|4 | 1.94M/41.5M [01:04<20:37, 33.5kB/s]
+ 5%|4 | 1.95M/41.5M [01:04<19:04, 36.2kB/s]
+ 5%|4 | 1.95M/41.5M [01:04<17:58, 38.5kB/s]
+ 5%|4 | 1.96M/41.5M [01:04<17:11, 40.2kB/s]
+ 5%|4 | 1.98M/41.5M [01:05<12:48, 53.9kB/s]
+ 5%|4 | 1.98M/41.5M [01:05<13:26, 51.4kB/s]
+ 5%|4 | 2.00M/41.5M [01:05<11:03, 62.4kB/s]
+ 5%|4 | 2.01M/41.5M [01:05<12:02, 57.3kB/s]
+ 5%|4 | 2.02M/41.5M [01:05<10:20, 66.7kB/s]
+ 5%|4 | 2.05M/41.5M [01:05<07:56, 86.8kB/s]
+ 5%|4 | 2.07M/41.5M [01:06<06:49, 101kB/s]
+ 5%|5 | 2.09M/41.5M [01:06<06:11, 111kB/s]
+ 5%|5 | 2.12M/41.5M [01:06<05:49, 118kB/s]
+ 5%|5 | 2.16M/41.5M [01:06<04:35, 150kB/s]
+ 5%|5 | 2.19M/41.5M [01:06<04:19, 159kB/s]
+ 5%|5 | 2.23M/41.5M [01:07<03:34, 192kB/s]
+ 5%|5 | 2.28M/41.5M [01:07<03:10, 215kB/s]
+ 6%|5 | 2.34M/41.5M [01:07<02:47, 245kB/s]
+ 6%|5 | 2.39M/41.5M [01:07<02:34, 266kB/s]
+ 6%|5 | 2.46M/41.5M [01:07<02:19, 294kB/s]
+ 6%|6 | 2.53M/41.5M [01:08<02:19, 293kB/s]
+ 6%|6 | 2.62M/41.5M [01:08<02:54, 234kB/s]
+ 6%|6 | 2.65M/41.5M [01:09<04:11, 162kB/s]
+ 7%|6 | 2.74M/41.5M [01:09<03:10, 213kB/s]
+ 7%|6 | 2.83M/41.5M [01:09<02:43, 247kB/s]
+ 7%|6 | 2.87M/41.5M [01:09<02:59, 226kB/s]
+ 7%|6 | 2.90M/41.5M [01:10<03:24, 198kB/s]
+ 7%|7 | 2.93M/41.5M [01:10<03:45, 179kB/s]
+ 7%|7 | 2.95M/41.5M [01:10<05:35, 120kB/s]
+ 7%|7 | 2.98M/41.5M [01:11<05:30, 122kB/s]
+ 7%|7 | 3.00M/41.5M [01:11<06:15, 108kB/s]
+ 7%|7 | 3.02M/41.5M [01:11<07:56, 84.7kB/s]
+ 7%|7 | 3.04M/41.5M [01:12<10:40, 62.9kB/s]
+ 7%|7 | 3.06M/41.5M [01:12<09:36, 69.9kB/s]
+ 7%|7 | 3.08M/41.5M [01:12<09:50, 68.2kB/s]
+ 7%|7 | 3.09M/41.5M [01:13<11:15, 59.6kB/s]
+ 7%|7 | 3.10M/41.5M [01:13<13:56, 48.1kB/s]
+ 7%|7 | 3.11M/41.5M [01:13<15:05, 44.4kB/s]
+ 8%|7 | 3.12M/41.5M [01:14<16:57, 39.5kB/s]
+ 8%|7 | 3.14M/41.5M [01:15<18:13, 36.8kB/s]
+ 8%|7 | 3.15M/41.5M [01:15<18:42, 35.8kB/s]
+ 8%|7 | 3.16M/41.5M [01:15<19:09, 35.0kB/s]
+ 8%|7 | 3.16M/41.5M [01:15<19:34, 34.2kB/s]
+ 8%|7 | 3.17M/41.5M [01:16<19:53, 33.7kB/s]
+ 8%|7 | 3.18M/41.5M [01:16<20:08, 33.2kB/s]
+ 8%|7 | 3.19M/41.5M [01:16<20:20, 32.9kB/s]
+ 8%|7 | 3.20M/41.5M [01:16<20:29, 32.7kB/s]
+ 8%|7 | 3.20M/41.5M [01:17<20:35, 32.5kB/s]
+ 8%|7 | 3.21M/41.5M [01:17<20:40, 32.4kB/s]
+ 8%|7 | 3.22M/41.5M [01:18<39:06, 17.1kB/s]
+ 8%|7 | 3.23M/41.5M [01:18<30:48, 21.7kB/s]
+ 8%|7 | 3.24M/41.5M [01:19<33:30, 20.0kB/s]
+ 8%|7 | 3.26M/41.5M [01:19<23:59, 27.9kB/s]
+ 8%|7 | 3.27M/41.5M [01:19<23:17, 28.7kB/s]
+ 8%|7 | 3.27M/41.5M [01:20<27:47, 24.0kB/s]
+ 8%|7 | 3.28M/41.5M [01:20<31:23, 21.3kB/s]
+ 8%|7 | 3.29M/41.5M [01:21<28:31, 23.4kB/s]
+ 8%|7 | 3.30M/41.5M [01:22<43:49, 15.2kB/s]
+ 8%|7 | 3.30M/41.5M [01:22<37:16, 17.9kB/s]
+ 8%|7 | 3.31M/41.5M [01:22<38:32, 17.3kB/s]
+ 8%|8 | 3.32M/41.5M [01:23<45:32, 14.6kB/s]
+ 8%|8 | 3.34M/41.5M [01:23<29:32, 22.6kB/s]
+ 8%|8 | 3.34M/41.5M [01:24<36:30, 18.3kB/s]
+ 8%|8 | 3.36M/41.5M [01:24<26:42, 25.0kB/s]
+ 8%|8 | 3.37M/41.5M [01:26<45:05, 14.8kB/s]
+ 8%|8 | 3.38M/41.5M [01:26<31:24, 21.2kB/s]
+ 8%|8 | 3.39M/41.5M [01:26<29:51, 22.3kB/s]
+ 8%|8 | 3.40M/41.5M [01:27<27:41, 24.0kB/s]
+ 8%|8 | 3.41M/41.5M [01:27<25:55, 25.7kB/s]
+ 8%|8 | 3.41M/41.5M [01:27<24:32, 27.1kB/s]
+ 8%|8 | 3.42M/41.5M [01:27<23:30, 28.3kB/s]
+ 8%|8 | 3.43M/41.5M [01:28<22:43, 29.3kB/s]
+ 8%|8 | 3.44M/41.5M [01:28<22:08, 30.0kB/s]
+ 8%|8 | 3.45M/41.5M [01:28<20:41, 32.1kB/s]
+ 8%|8 | 3.45M/41.5M [01:28<17:00, 39.1kB/s]
+ 8%|8 | 3.46M/41.5M [01:28<16:43, 39.7kB/s]
+ 8%|8 | 3.47M/41.5M [01:29<16:52, 39.4kB/s]
+ 8%|8 | 3.48M/41.5M [01:29<14:15, 46.6kB/s]
+ 8%|8 | 3.48M/41.5M [01:29<22:21, 29.7kB/s]
+ 8%|8 | 3.50M/41.5M [01:29<16:50, 39.4kB/s]
+ 8%|8 | 3.51M/41.5M [01:30<22:54, 29.0kB/s]
+ 8%|8 | 3.52M/41.5M [01:30<17:44, 37.4kB/s]
+ 9%|8 | 3.53M/41.5M [01:31<18:24, 36.0kB/s]
+ 9%|8 | 3.54M/41.5M [01:31<19:56, 33.3kB/s]
+ 9%|8 | 3.55M/41.5M [01:31<19:06, 34.7kB/s]
+ 9%|8 | 3.55M/41.5M [01:31<19:32, 33.9kB/s]
+ 9%|8 | 3.56M/41.5M [01:33<47:41, 13.9kB/s]
+ 9%|8 | 3.57M/41.5M [01:33<39:58, 16.6kB/s]
+ 9%|8 | 3.58M/41.5M [01:34<46:22, 14.3kB/s]
+ 9%|8 | 3.59M/41.5M [01:34<44:53, 14.8kB/s]
+ 9%|8 | 3.59M/41.5M [01:35<56:00, 11.8kB/s]
+ 9%|8 | 3.60M/41.5M [01:36<56:34, 11.7kB/s]
+ 9%|8 | 3.61M/41.5M [01:36<48:04, 13.8kB/s]
+ 9%|8 | 3.62M/41.5M [01:37<59:47, 11.1kB/s]
+ 9%|8 | 3.62M/41.5M [01:38<50:43, 13.0kB/s]
+ 9%|8 | 3.63M/41.5M [01:38<39:56, 16.6kB/s]
+ 9%|8 | 3.64M/41.5M [01:38<36:47, 18.0kB/s]
+ 9%|8 | 3.65M/41.5M [01:39<30:10, 21.9kB/s]
+ 9%|8 | 3.66M/41.5M [01:39<25:32, 25.9kB/s]
+ 9%|8 | 3.66M/41.5M [01:39<22:17, 29.7kB/s]
+ 9%|8 | 3.67M/41.5M [01:39<20:00, 33.0kB/s]
+ 9%|8 | 3.68M/41.5M [01:39<18:25, 35.9kB/s]
+ 9%|8 | 3.69M/41.5M [01:39<17:18, 38.2kB/s]
+ 9%|8 | 3.70M/41.5M [01:40<16:31, 40.0kB/s]
+ 9%|8 | 3.71M/41.5M [01:40<12:17, 53.7kB/s]
+ 9%|8 | 3.72M/41.5M [01:40<12:52, 51.3kB/s]
+ 9%|9 | 3.73M/41.5M [01:40<10:34, 62.4kB/s]
+ 9%|9 | 3.74M/41.5M [01:40<11:30, 57.3kB/s]
+ 9%|9 | 3.76M/41.5M [01:41<09:51, 66.9kB/s]
+ 9%|9 | 3.78M/41.5M [01:41<07:34, 87.0kB/s]
+ 9%|9 | 3.80M/41.5M [01:41<06:30, 101kB/s]
+ 9%|9 | 3.83M/41.5M [01:41<05:55, 111kB/s]
+ 9%|9 | 3.85M/41.5M [01:41<05:33, 118kB/s]
+ 9%|9 | 3.89M/41.5M [01:41<04:22, 150kB/s]
+ 9%|9 | 3.92M/41.5M [01:42<04:07, 159kB/s]
+ 10%|9 | 3.97M/41.5M [01:42<03:24, 192kB/s]
+ 10%|9 | 4.01M/41.5M [01:42<03:14, 202kB/s]
+ 10%|9 | 4.06M/41.5M [01:42<02:46, 236kB/s]
+ 10%|9 | 4.12M/41.5M [01:42<02:31, 259kB/s]
+ 10%|# | 4.19M/41.5M [01:43<02:09, 303kB/s]
+ 10%|# | 4.26M/41.5M [01:43<01:57, 333kB/s]
+ 10%|# | 4.34M/41.5M [01:43<01:45, 368kB/s]
+ 11%|# | 4.43M/41.5M [01:43<01:32, 419kB/s]
+ 11%|# | 4.53M/41.5M [01:43<01:24, 461kB/s]
+ 11%|#1 | 4.64M/41.5M [01:44<01:21, 474kB/s]
+ 11%|#1 | 4.76M/41.5M [01:44<01:20, 476kB/s]
+ 12%|#1 | 4.80M/41.5M [01:44<01:41, 380kB/s]
+ 12%|#1 | 4.87M/41.5M [01:45<02:36, 246kB/s]
+ 12%|#1 | 4.95M/41.5M [01:45<02:14, 285kB/s]
+ 12%|#2 | 5.05M/41.5M [01:45<01:59, 321kB/s]
+ 12%|#2 | 5.12M/41.5M [01:45<02:05, 303kB/s]
+ 12%|#2 | 5.16M/41.5M [01:46<03:07, 204kB/s]
+ 13%|#2 | 5.24M/41.5M [01:46<03:16, 193kB/s]
+ 13%|#2 | 5.30M/41.5M [01:47<03:43, 170kB/s]
+ 13%|#2 | 5.33M/41.5M [01:47<04:04, 155kB/s]
+ 13%|#2 | 5.37M/41.5M [01:47<04:02, 156kB/s]
+ 13%|#2 | 5.39M/41.5M [01:48<06:38, 95.0kB/s]
+ 13%|#3 | 5.41M/41.5M [01:48<07:04, 89.1kB/s]
+ 13%|#3 | 5.42M/41.5M [01:49<10:43, 58.8kB/s]
+ 13%|#3 | 5.43M/41.5M [01:50<13:42, 46.0kB/s]
+ 13%|#3 | 5.44M/41.5M [01:50<17:01, 37.0kB/s]
+ 13%|#3 | 5.45M/41.5M [01:50<15:04, 41.8kB/s]
+ 13%|#3 | 5.46M/41.5M [01:51<15:48, 39.8kB/s]
+ 13%|#3 | 5.47M/41.5M [01:51<20:12, 31.1kB/s]
+ 13%|#3 | 5.48M/41.5M [01:52<26:50, 23.4kB/s]
+ 13%|#3 | 5.50M/41.5M [01:53<24:26, 25.7kB/s]
+ 13%|#3 | 5.51M/41.5M [01:53<23:30, 26.7kB/s]
+ 13%|#3 | 5.52M/41.5M [01:55<42:53, 14.7kB/s]
+ 13%|#3 | 5.52M/41.5M [01:56<54:52, 11.5kB/s]
+ 13%|#3 | 5.53M/41.5M [01:56<45:59, 13.7kB/s]
+ 13%|#3 | 5.54M/41.5M [01:57<53:26, 11.8kB/s]
+ 13%|#3 | 5.55M/41.5M [01:58<1:00:17, 10.4kB/s]
+ 13%|#3 | 5.56M/41.5M [01:58<42:23, 14.8kB/s]
+ 13%|#3 | 5.57M/41.5M [01:59<41:37, 15.1kB/s]
+ 13%|#3 | 5.58M/41.5M [01:59<36:00, 17.4kB/s]
+ 13%|#3 | 5.59M/41.5M [02:00<31:37, 19.8kB/s]
+ 13%|#3 | 5.59M/41.5M [02:00<29:10, 21.5kB/s]
+ 14%|#3 | 5.60M/41.5M [02:00<25:32, 24.5kB/s]
+ 14%|#3 | 5.61M/41.5M [02:00<23:48, 26.3kB/s]
+ 14%|#3 | 5.62M/41.5M [02:01<22:33, 27.8kB/s]
+ 14%|#3 | 5.62M/41.5M [02:01<21:39, 28.9kB/s]
+ 14%|#3 | 5.64M/41.5M [02:01<16:59, 36.9kB/s]
+ 14%|#3 | 5.65M/41.5M [02:01<16:48, 37.3kB/s]
+ 14%|#3 | 5.66M/41.5M [02:02<18:21, 34.1kB/s]
+ 14%|#3 | 5.66M/41.5M [02:02<17:48, 35.2kB/s]
+ 14%|#3 | 5.67M/41.5M [02:03<30:03, 20.8kB/s]
+ 14%|#3 | 5.69M/41.5M [02:04<33:59, 18.4kB/s]
+ 14%|#3 | 5.70M/41.5M [02:04<39:52, 15.7kB/s]
+ 14%|#3 | 5.70M/41.5M [02:05<34:39, 18.0kB/s]
+ 14%|#3 | 5.71M/41.5M [02:05<30:36, 20.4kB/s]
+ 14%|#3 | 5.72M/41.5M [02:05<27:32, 22.7kB/s]
+ 14%|#3 | 5.73M/41.5M [02:06<36:19, 17.2kB/s]
+ 14%|#3 | 5.73M/41.5M [02:09<1:29:45, 6.96kB/s]
+ 14%|#3 | 5.74M/41.5M [02:10<1:19:26, 7.86kB/s]
+ 14%|#3 | 5.75M/41.5M [02:11<1:33:48, 6.66kB/s]
+ 14%|#3 | 5.76M/41.5M [02:13<1:39:25, 6.28kB/s]
+ 14%|#3 | 5.77M/41.5M [02:13<1:25:33, 7.30kB/s]
+ 14%|#3 | 5.77M/41.5M [02:14<1:08:20, 9.13kB/s]
+ 14%|#3 | 5.79M/41.5M [02:14<40:05, 15.6kB/s]
+ 14%|#3 | 5.80M/41.5M [02:14<33:36, 18.6kB/s]
+ 14%|#3 | 5.80M/41.5M [02:14<28:26, 21.9kB/s]
+ 14%|#4 | 5.81M/41.5M [02:15<24:29, 25.5kB/s]
+ 14%|#4 | 5.82M/41.5M [02:15<21:31, 29.0kB/s]
+ 14%|#4 | 5.83M/41.5M [02:15<19:19, 32.2kB/s]
+ 14%|#4 | 5.84M/41.5M [02:15<13:45, 45.3kB/s]
+ 14%|#4 | 5.85M/41.5M [02:15<13:46, 45.2kB/s]
+ 14%|#4 | 5.86M/41.5M [02:15<13:47, 45.1kB/s]
+ 14%|#4 | 5.88M/41.5M [02:16<11:33, 53.9kB/s]
+ 14%|#4 | 5.88M/41.5M [02:16<11:21, 54.8kB/s]
+ 14%|#4 | 5.90M/41.5M [02:16<10:12, 60.9kB/s]
+ 14%|#4 | 5.91M/41.5M [02:16<09:00, 69.0kB/s]
+ 14%|#4 | 5.92M/41.5M [02:16<09:21, 66.4kB/s]
+ 14%|#4 | 5.94M/41.5M [02:17<09:01, 68.8kB/s]
+ 14%|#4 | 5.95M/41.5M [02:17<08:17, 74.9kB/s]
+ 14%|#4 | 5.97M/41.5M [02:17<07:50, 79.2kB/s]
+ 14%|#4 | 5.98M/41.5M [02:17<07:31, 82.4kB/s]
+ 14%|#4 | 6.00M/41.5M [02:17<07:19, 84.6kB/s]
+ 15%|#4 | 6.02M/41.5M [02:17<06:14, 99.4kB/s]
+ 15%|#4 | 6.04M/41.5M [02:18<06:24, 96.7kB/s]
+ 15%|#4 | 6.05M/41.5M [02:18<06:28, 95.6kB/s]
+ 15%|#4 | 6.08M/41.5M [02:18<05:49, 106kB/s]
+ 15%|#4 | 6.09M/41.5M [02:18<06:02, 102kB/s]
+ 15%|#4 | 6.12M/41.5M [02:18<05:30, 112kB/s]
+ 15%|#4 | 6.14M/41.5M [02:19<05:11, 119kB/s]
+ 15%|#4 | 6.17M/41.5M [02:19<04:29, 137kB/s]
+ 15%|#4 | 6.20M/41.5M [02:19<04:06, 150kB/s]
+ 15%|#5 | 6.23M/41.5M [02:19<03:52, 159kB/s]
+ 15%|#5 | 6.27M/41.5M [02:19<03:26, 179kB/s]
+ 15%|#5 | 6.32M/41.5M [02:19<03:06, 198kB/s]
+ 15%|#5 | 6.37M/41.5M [02:20<03:04, 200kB/s]
+ 15%|#5 | 6.41M/41.5M [02:21<06:53, 88.9kB/s]
+ 15%|#5 | 6.43M/41.5M [02:21<06:47, 90.2kB/s]
+ 16%|#5 | 6.54M/41.5M [02:21<03:39, 167kB/s]
+ 16%|#5 | 6.56M/41.5M [02:22<04:03, 151kB/s]
+ 16%|#5 | 6.59M/41.5M [02:22<05:34, 109kB/s]
+ 16%|#5 | 6.61M/41.5M [02:22<05:43, 106kB/s]
+ 16%|#5 | 6.63M/41.5M [02:23<05:51, 104kB/s]
+ 16%|#6 | 6.65M/41.5M [02:23<08:10, 74.5kB/s]
+ 16%|#6 | 6.66M/41.5M [02:25<21:22, 28.5kB/s]
+ 16%|#6 | 6.70M/41.5M [02:25<15:18, 39.7kB/s]
+ 16%|#6 | 6.71M/41.5M [02:27<25:00, 24.3kB/s]
+ 16%|#6 | 6.74M/41.5M [02:27<17:28, 34.7kB/s]
+ 16%|#6 | 6.76M/41.5M [02:28<15:47, 38.4kB/s]
+ 16%|#6 | 6.77M/41.5M [02:28<14:19, 42.3kB/s]
+ 16%|#6 | 6.78M/41.5M [02:28<14:58, 40.5kB/s]
+ 16%|#6 | 6.79M/41.5M [02:28<15:37, 38.8kB/s]
+ 16%|#6 | 6.80M/41.5M [02:29<19:55, 30.4kB/s]
+ 16%|#6 | 6.81M/41.5M [02:29<20:07, 30.1kB/s]
+ 16%|#6 | 6.83M/41.5M [02:30<25:26, 23.8kB/s]
+ 16%|#6 | 6.84M/41.5M [02:31<24:10, 25.1kB/s]
+ 16%|#6 | 6.84M/41.5M [02:31<23:01, 26.3kB/s]
+ 17%|#6 | 6.85M/41.5M [02:31<22:01, 27.5kB/s]
+ 17%|#6 | 6.87M/41.5M [02:31<16:55, 35.7kB/s]
+ 17%|#6 | 6.88M/41.5M [02:32<17:21, 34.9kB/s]
+ 17%|#6 | 6.88M/41.5M [02:32<26:49, 22.5kB/s]
+ 17%|#6 | 6.90M/41.5M [02:33<23:35, 25.6kB/s]
+ 17%|#6 | 6.91M/41.5M [02:33<18:22, 32.9kB/s]
+ 17%|#6 | 6.92M/41.5M [02:34<22:25, 26.9kB/s]
+ 17%|#6 | 6.94M/41.5M [02:34<17:33, 34.4kB/s]
+ 17%|#6 | 6.95M/41.5M [02:35<36:53, 16.4kB/s]
+ 17%|#6 | 6.95M/41.5M [02:36<32:42, 18.4kB/s]
+ 17%|#6 | 6.97M/41.5M [02:36<23:26, 25.7kB/s]
+ 17%|#6 | 6.98M/41.5M [02:36<22:24, 26.9kB/s]
+ 17%|#6 | 6.98M/41.5M [02:36<21:33, 28.0kB/s]
+ 17%|#6 | 6.99M/41.5M [02:37<25:40, 23.5kB/s]
+ 17%|#6 | 7.01M/41.5M [02:38<26:05, 23.1kB/s]
+ 17%|#6 | 7.02M/41.5M [02:38<20:59, 28.7kB/s]
+ 17%|#6 | 7.03M/41.5M [02:39<36:29, 16.5kB/s]
+ 17%|#6 | 7.04M/41.5M [02:40<32:22, 18.6kB/s]
+ 17%|#6 | 7.05M/41.5M [02:40<28:58, 20.8kB/s]
+ 17%|#7 | 7.05M/41.5M [02:40<30:17, 19.9kB/s]
+ 17%|#7 | 7.07M/41.5M [02:41<32:31, 18.5kB/s]
+ 17%|#7 | 7.08M/41.5M [02:42<43:22, 13.9kB/s]
+ 17%|#7 | 7.09M/41.5M [02:43<37:10, 16.2kB/s]
+ 17%|#7 | 7.09M/41.5M [02:43<37:14, 16.1kB/s]
+ 17%|#7 | 7.10M/41.5M [02:44<37:18, 16.1kB/s]
+ 17%|#7 | 7.11M/41.5M [02:44<37:22, 16.1kB/s]
+ 17%|#7 | 7.12M/41.5M [02:45<37:23, 16.1kB/s]
+ 17%|#7 | 7.12M/41.5M [02:45<37:25, 16.0kB/s]
+ 17%|#7 | 7.13M/41.5M [02:46<48:24, 12.4kB/s]
+ 17%|#7 | 7.14M/41.5M [02:46<39:37, 15.1kB/s]
+ 17%|#7 | 7.15M/41.5M [02:47<38:58, 15.4kB/s]
+ 17%|#7 | 7.16M/41.5M [02:48<44:05, 13.6kB/s]
+ 17%|#7 | 7.16M/41.5M [02:48<47:40, 12.6kB/s]
+ 17%|#7 | 7.17M/41.5M [02:49<39:00, 15.4kB/s]
+ 17%|#7 | 7.18M/41.5M [02:49<38:32, 15.6kB/s]
+ 17%|#7 | 7.19M/41.5M [02:50<35:52, 16.7kB/s]
+ 17%|#7 | 7.20M/41.5M [02:50<29:06, 20.6kB/s]
+ 17%|#7 | 7.20M/41.5M [02:50<28:22, 21.1kB/s]
+ 17%|#7 | 7.21M/41.5M [02:50<23:51, 25.1kB/s]
+ 17%|#7 | 7.22M/41.5M [02:51<24:41, 24.2kB/s]
+ 17%|#7 | 7.23M/41.5M [02:51<16:22, 36.6kB/s]
+ 17%|#7 | 7.24M/41.5M [02:51<16:20, 36.6kB/s]
+ 17%|#7 | 7.25M/41.5M [02:51<15:32, 38.5kB/s]
+ 17%|#7 | 7.26M/41.5M [02:51<14:56, 40.1kB/s]
+ 18%|#7 | 7.27M/41.5M [02:52<13:39, 43.8kB/s]
+ 18%|#7 | 7.27M/41.5M [02:52<13:33, 44.1kB/s]
+ 18%|#7 | 7.29M/41.5M [02:52<11:06, 53.8kB/s]
+ 18%|#7 | 7.30M/41.5M [02:52<11:38, 51.3kB/s]
+ 18%|#7 | 7.30M/41.5M [02:52<11:18, 52.8kB/s]
+ 18%|#7 | 7.32M/41.5M [02:53<09:19, 64.0kB/s]
+ 18%|#7 | 7.34M/41.5M [02:53<08:18, 71.8kB/s]
+ 18%|#7 | 7.35M/41.5M [02:53<08:14, 72.4kB/s]
+ 18%|#7 | 7.36M/41.5M [02:53<08:39, 68.9kB/s]
+ 18%|#7 | 7.38M/41.5M [02:53<07:54, 75.3kB/s]
+ 18%|#7 | 7.39M/41.5M [02:53<07:28, 79.7kB/s]
+ 18%|#7 | 7.41M/41.5M [02:54<07:11, 82.8kB/s]
+ 18%|#7 | 7.42M/41.5M [02:54<07:00, 84.9kB/s]
+ 18%|#7 | 7.45M/41.5M [02:54<05:57, 99.9kB/s]
+ 18%|#7 | 7.46M/41.5M [02:54<06:08, 96.9kB/s]
+ 18%|#8 | 7.48M/41.5M [02:54<05:29, 108kB/s]
+ 18%|#8 | 7.51M/41.5M [02:55<05:06, 116kB/s]
+ 18%|#8 | 7.54M/41.5M [02:55<04:23, 135kB/s]
+ 18%|#8 | 7.57M/41.5M [02:55<03:59, 148kB/s]
+ 18%|#8 | 7.61M/41.5M [02:55<03:27, 171kB/s]
+ 18%|#8 | 7.66M/41.5M [02:55<02:56, 201kB/s]
+ 19%|#8 | 7.70M/41.5M [02:55<02:41, 219kB/s]
+ 19%|#8 | 7.75M/41.5M [02:56<02:21, 249kB/s]
+ 19%|#8 | 7.80M/41.5M [02:56<02:20, 251kB/s]
+ 19%|#8 | 7.83M/41.5M [02:58<10:55, 53.8kB/s]
+ 19%|#8 | 7.88M/41.5M [02:58<08:15, 71.1kB/s]
+ 19%|#9 | 8.01M/41.5M [02:59<05:19, 110kB/s]
+ 19%|#9 | 8.05M/41.5M [03:00<06:02, 96.8kB/s]
+ 19%|#9 | 8.07M/41.5M [03:00<06:20, 92.2kB/s]
+ 20%|#9 | 8.18M/41.5M [03:00<03:50, 151kB/s]
+ 20%|#9 | 8.20M/41.5M [03:00<04:07, 141kB/s]
+ 20%|#9 | 8.23M/41.5M [03:01<07:05, 82.0kB/s]
+ 20%|#9 | 8.30M/41.5M [03:03<08:06, 71.6kB/s]
+ 20%|## | 8.31M/41.5M [03:03<08:12, 70.6kB/s]
+ 20%|## | 8.34M/41.5M [03:04<11:03, 52.4kB/s]
+ 20%|## | 8.42M/41.5M [03:04<06:16, 92.1kB/s]
+ 20%|## | 8.45M/41.5M [03:04<06:26, 89.7kB/s]
+ 20%|## | 8.46M/41.5M [03:05<08:00, 72.1kB/s]
+ 20%|## | 8.49M/41.5M [03:05<07:00, 82.2kB/s]
+ 21%|## | 8.51M/41.5M [03:05<07:20, 78.5kB/s]
+ 21%|## | 8.52M/41.5M [03:06<07:39, 75.3kB/s]
+ 21%|## | 8.55M/41.5M [03:06<07:10, 80.3kB/s]
+ 21%|## | 8.56M/41.5M [03:06<09:30, 60.5kB/s]
+ 21%|## | 8.59M/41.5M [03:07<10:18, 55.8kB/s]
+ 21%|## | 8.61M/41.5M [03:08<12:17, 46.7kB/s]
+ 21%|## | 8.62M/41.5M [03:08<15:37, 36.7kB/s]
+ 21%|## | 8.63M/41.5M [03:09<15:56, 36.0kB/s]
+ 21%|## | 8.64M/41.5M [03:09<16:16, 35.3kB/s]
+ 21%|## | 8.65M/41.5M [03:09<16:35, 34.6kB/s]
+ 21%|## | 8.66M/41.5M [03:09<16:52, 34.0kB/s]
+ 21%|## | 8.66M/41.5M [03:10<21:20, 26.9kB/s]
+ 21%|## | 8.67M/41.5M [03:11<27:07, 21.1kB/s]
+ 21%|## | 8.68M/41.5M [03:11<24:40, 23.2kB/s]
+ 21%|## | 8.69M/41.5M [03:11<25:23, 22.6kB/s]
+ 21%|## | 8.70M/41.5M [03:12<23:16, 24.6kB/s]
+ 21%|## | 8.70M/41.5M [03:12<21:43, 26.4kB/s]
+ 21%|## | 8.71M/41.5M [03:13<30:59, 18.5kB/s]
+ 21%|##1 | 8.72M/41.5M [03:13<27:08, 21.1kB/s]
+ 21%|##1 | 8.73M/41.5M [03:13<24:23, 23.5kB/s]
+ 21%|##1 | 8.73M/41.5M [03:13<22:26, 25.5kB/s]
+ 21%|##1 | 8.74M/41.5M [03:14<31:42, 18.1kB/s]
+ 21%|##1 | 8.76M/41.5M [03:14<21:13, 27.0kB/s]
+ 21%|##1 | 8.77M/41.5M [03:15<34:24, 16.6kB/s]
+ 21%|##1 | 8.78M/41.5M [03:16<27:32, 20.8kB/s]
+ 21%|##1 | 8.79M/41.5M [03:16<25:18, 22.6kB/s]
+ 21%|##1 | 8.80M/41.5M [03:16<23:28, 24.3kB/s]
+ 21%|##1 | 8.80M/41.5M [03:17<21:59, 26.0kB/s]
+ 21%|##1 | 8.81M/41.5M [03:17<20:51, 27.4kB/s]
+ 21%|##1 | 8.82M/41.5M [03:18<38:50, 14.7kB/s]
+ 21%|##1 | 8.84M/41.5M [03:19<30:23, 18.8kB/s]
+ 21%|##1 | 8.84M/41.5M [03:19<27:21, 20.9kB/s]
+ 21%|##1 | 8.85M/41.5M [03:19<28:28, 20.0kB/s]
+ 21%|##1 | 8.87M/41.5M [03:20<28:31, 20.0kB/s]
+ 21%|##1 | 8.88M/41.5M [03:21<37:31, 15.2kB/s]
+ 21%|##1 | 8.88M/41.5M [03:21<32:37, 17.5kB/s]
+ 21%|##1 | 8.89M/41.5M [03:22<38:04, 15.0kB/s]
+ 21%|##1 | 8.90M/41.5M [03:23<46:02, 12.4kB/s]
+ 21%|##1 | 8.91M/41.5M [03:23<38:07, 14.9kB/s]
+ 21%|##1 | 8.91M/41.5M [03:24<37:23, 15.2kB/s]
+ 22%|##1 | 8.92M/41.5M [03:24<31:41, 18.0kB/s]
+ 22%|##1 | 8.93M/41.5M [03:24<27:36, 20.6kB/s]
+ 22%|##1 | 8.94M/41.5M [03:25<24:41, 23.0kB/s]
+ 22%|##1 | 8.95M/41.5M [03:25<22:37, 25.1kB/s]
+ 22%|##1 | 8.95M/41.5M [03:25<25:51, 22.0kB/s]
+ 22%|##1 | 8.97M/41.5M [03:26<19:47, 28.7kB/s]
+ 22%|##1 | 8.98M/41.5M [03:26<18:01, 31.5kB/s]
+ 22%|##1 | 8.98M/41.5M [03:26<16:36, 34.2kB/s]
+ 22%|##1 | 9.00M/41.5M [03:26<12:49, 44.3kB/s]
+ 22%|##1 | 9.01M/41.5M [03:27<12:06, 46.9kB/s]
+ 22%|##1 | 9.02M/41.5M [03:27<12:14, 46.4kB/s]
+ 22%|##1 | 9.02M/41.5M [03:27<12:20, 46.0kB/s]
+ 22%|##1 | 9.04M/41.5M [03:27<09:44, 58.2kB/s]
+ 22%|##1 | 9.05M/41.5M [03:27<10:25, 54.4kB/s]
+ 22%|##1 | 9.06M/41.5M [03:27<08:45, 64.7kB/s]
+ 22%|##1 | 9.08M/41.5M [03:28<08:23, 67.6kB/s]
+ 22%|##1 | 9.09M/41.5M [03:28<08:40, 65.3kB/s]
+ 22%|##1 | 9.10M/41.5M [03:28<08:18, 68.1kB/s]
+ 22%|##1 | 9.11M/41.5M [03:28<08:36, 65.8kB/s]
+ 22%|##1 | 9.12M/41.5M [03:28<07:44, 73.1kB/s]
+ 22%|##2 | 9.14M/41.5M [03:29<07:13, 78.2kB/s]
+ 22%|##2 | 9.16M/41.5M [03:29<06:54, 81.7kB/s]
+ 22%|##2 | 9.18M/41.5M [03:29<06:10, 91.5kB/s]
+ 22%|##2 | 9.20M/41.5M [03:29<06:12, 91.0kB/s]
+ 22%|##2 | 9.21M/41.5M [03:29<05:48, 97.0kB/s]
+ 22%|##2 | 9.23M/41.5M [03:30<05:32, 102kB/s]
+ 22%|##2 | 9.25M/41.5M [03:30<05:21, 105kB/s]
+ 22%|##2 | 9.27M/41.5M [03:30<05:16, 107kB/s]
+ 22%|##2 | 9.29M/41.5M [03:30<05:09, 109kB/s]
+ 22%|##2 | 9.31M/41.5M [03:30<04:48, 117kB/s]
+ 23%|##2 | 9.34M/41.5M [03:30<04:35, 122kB/s]
+ 23%|##2 | 9.36M/41.5M [03:31<04:27, 126kB/s]
+ 23%|##2 | 9.39M/41.5M [03:31<04:12, 133kB/s]
+ 23%|##2 | 9.41M/41.5M [03:31<03:54, 143kB/s]
+ 23%|##2 | 9.45M/41.5M [03:31<03:37, 154kB/s]
+ 23%|##2 | 9.48M/41.5M [03:31<03:27, 162kB/s]
+ 23%|##2 | 9.52M/41.5M [03:32<03:06, 180kB/s]
+ 23%|##3 | 9.55M/41.5M [03:32<02:44, 204kB/s]
+ 23%|##3 | 9.58M/41.5M [03:32<03:03, 182kB/s]
+ 23%|##3 | 9.61M/41.5M [03:32<02:52, 194kB/s]
+ 23%|##3 | 9.63M/41.5M [03:32<04:13, 132kB/s]
+ 23%|##3 | 9.65M/41.5M [03:33<09:45, 57.1kB/s]
+ 23%|##3 | 9.73M/41.5M [03:34<04:50, 115kB/s]
+ 24%|##3 | 9.77M/41.5M [03:34<04:43, 117kB/s]
+ 24%|##3 | 9.79M/41.5M [03:35<07:01, 78.8kB/s]
+ 24%|##3 | 9.82M/41.5M [03:35<06:16, 88.3kB/s]
+ 24%|##3 | 9.86M/41.5M [03:35<05:19, 104kB/s]
+ 24%|##3 | 9.88M/41.5M [03:35<05:25, 102kB/s]
+ 24%|##3 | 9.91M/41.5M [03:36<05:05, 108kB/s]
+ 24%|##3 | 9.94M/41.5M [03:36<05:14, 105kB/s]
+ 24%|##3 | 9.95M/41.5M [03:37<11:59, 46.0kB/s]
+ 24%|##4 | 9.98M/41.5M [03:37<09:18, 59.2kB/s]
+ 24%|##4 | 10.0M/41.5M [03:38<08:19, 66.1kB/s]
+ 24%|##4 | 10.0M/41.5M [03:39<13:40, 40.2kB/s]
+ 24%|##4 | 10.0M/41.5M [03:39<13:00, 42.3kB/s]
+ 24%|##4 | 10.1M/41.5M [03:39<11:35, 47.4kB/s]
+ 24%|##4 | 10.1M/41.5M [03:40<17:06, 32.1kB/s]
+ 24%|##4 | 10.1M/41.5M [03:41<22:47, 24.1kB/s]
+ 24%|##4 | 10.1M/41.5M [03:41<18:12, 30.1kB/s]
+ 24%|##4 | 10.1M/41.5M [03:41<18:00, 30.5kB/s]
+ 24%|##4 | 10.1M/41.5M [03:42<21:26, 25.6kB/s]
+ 24%|##4 | 10.1M/41.5M [03:42<16:36, 33.0kB/s]
+ 24%|##4 | 10.1M/41.5M [03:43<23:57, 22.9kB/s]
+ 24%|##4 | 10.1M/41.5M [03:43<18:08, 30.2kB/s]
+ 24%|##4 | 10.2M/41.5M [03:43<17:55, 30.5kB/s]
+ 25%|##4 | 10.2M/41.5M [03:44<14:23, 38.0kB/s]
+ 25%|##4 | 10.2M/41.5M [03:44<14:57, 36.6kB/s]
+ 25%|##4 | 10.2M/41.5M [03:44<12:31, 43.6kB/s]
+ 25%|##4 | 10.2M/41.5M [03:44<13:29, 40.5kB/s]
+ 25%|##4 | 10.2M/41.5M [03:45<14:18, 38.2kB/s]
+ 25%|##4 | 10.2M/41.5M [03:45<15:55, 34.3kB/s]
+ 25%|##4 | 10.2M/41.5M [03:45<15:36, 35.0kB/s]
+ 25%|##4 | 10.2M/41.5M [03:46<13:21, 40.9kB/s]
+ 25%|##4 | 10.3M/41.5M [03:46<13:36, 40.1kB/s]
+ 25%|##4 | 10.3M/41.5M [03:46<18:27, 29.6kB/s]
+ 25%|##4 | 10.3M/41.5M [03:47<14:26, 37.7kB/s]
+ 25%|##4 | 10.3M/41.5M [03:47<15:00, 36.3kB/s]
+ 25%|##4 | 10.3M/41.5M [03:48<20:15, 26.9kB/s]
+ 25%|##4 | 10.3M/41.5M [03:48<18:45, 29.1kB/s]
+ 25%|##4 | 10.3M/41.5M [03:49<36:20, 15.0kB/s]
+ 25%|##4 | 10.3M/41.5M [03:50<27:56, 19.5kB/s]
+ 25%|##4 | 10.3M/41.5M [03:50<32:33, 16.7kB/s]
+ 25%|##4 | 10.3M/41.5M [03:51<40:36, 13.4kB/s]
+ 25%|##4 | 10.4M/41.5M [03:54<1:04:07, 8.48kB/s]
+ 25%|##4 | 10.4M/41.5M [03:54<53:15, 10.2kB/s]
+ 25%|##5 | 10.4M/41.5M [03:55<48:29, 11.2kB/s]
+ 25%|##5 | 10.4M/41.5M [03:55<40:15, 13.5kB/s]
+ 25%|##5 | 10.4M/41.5M [03:56<43:09, 12.6kB/s]
+ 25%|##5 | 10.4M/41.5M [03:57<44:19, 12.3kB/s]
+ 25%|##5 | 10.4M/41.5M [03:59<1:08:22, 7.94kB/s]
+ 25%|##5 | 10.4M/41.5M [04:00<1:08:14, 7.96kB/s]
+ 25%|##5 | 10.4M/41.5M [04:00<1:02:07, 8.74kB/s]
+ 25%|##5 | 10.4M/41.5M [04:01<49:50, 10.9kB/s]
+ 25%|##5 | 10.4M/41.5M [04:01<44:02, 12.3kB/s]
+ 25%|##5 | 10.4M/41.5M [04:02<43:57, 12.3kB/s]
+ 25%|##5 | 10.5M/41.5M [04:02<35:16, 15.4kB/s]
+ 25%|##5 | 10.5M/41.5M [04:02<28:19, 19.1kB/s]
+ 25%|##5 | 10.5M/41.5M [04:02<26:14, 20.7kB/s]
+ 25%|##5 | 10.5M/41.5M [04:03<22:50, 23.7kB/s]
+ 25%|##5 | 10.5M/41.5M [04:03<18:45, 28.9kB/s]
+ 25%|##5 | 10.5M/41.5M [04:03<16:44, 32.4kB/s]
+ 25%|##5 | 10.5M/41.5M [04:03<16:10, 33.5kB/s]
+ 25%|##5 | 10.5M/41.5M [04:03<14:56, 36.2kB/s]
+ 25%|##5 | 10.5M/41.5M [04:04<14:04, 38.5kB/s]
+ 25%|##5 | 10.5M/41.5M [04:04<12:36, 42.9kB/s]
+ 25%|##5 | 10.5M/41.5M [04:04<10:50, 49.9kB/s]
+ 25%|##5 | 10.5M/41.5M [04:04<10:01, 53.9kB/s]
+ 25%|##5 | 10.5M/41.5M [04:04<10:38, 50.8kB/s]
+ 25%|##5 | 10.6M/41.5M [04:04<09:23, 57.6kB/s]
+ 25%|##5 | 10.6M/41.5M [04:05<09:05, 59.4kB/s]
+ 26%|##5 | 10.6M/41.5M [04:05<07:48, 69.1kB/s]
+ 26%|##5 | 10.6M/41.5M [04:05<07:40, 70.3kB/s]
+ 26%|##5 | 10.6M/41.5M [04:05<07:05, 76.1kB/s]
+ 26%|##5 | 10.6M/41.5M [04:05<06:43, 80.2kB/s]
+ 26%|##5 | 10.6M/41.5M [04:05<06:29, 83.1kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<06:19, 85.1kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<06:13, 86.5kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<05:42, 94.3kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<05:14, 103kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<05:12, 103kB/s]
+ 26%|##5 | 10.7M/41.5M [04:06<04:52, 110kB/s]
+ 26%|##5 | 10.8M/41.5M [04:07<05:11, 103kB/s]
+ 26%|##5 | 10.8M/41.5M [04:07<04:43, 114kB/s]
+ 26%|##6 | 10.8M/41.5M [04:07<04:06, 130kB/s]
+ 26%|##6 | 10.8M/41.5M [04:07<03:39, 147kB/s]
+ 26%|##6 | 10.9M/41.5M [04:07<02:56, 182kB/s]
+ 26%|##6 | 10.9M/41.5M [04:07<03:09, 170kB/s]
+ 26%|##6 | 10.9M/41.5M [04:07<03:06, 172kB/s]
+ 26%|##6 | 10.9M/41.5M [04:08<02:48, 190kB/s]
+ 26%|##6 | 11.0M/41.5M [04:08<02:22, 225kB/s]
+ 27%|##6 | 11.0M/41.5M [04:08<02:28, 215kB/s]
+ 27%|##6 | 11.0M/41.5M [04:08<02:18, 230kB/s]
+ 27%|##6 | 11.1M/41.5M [04:08<02:27, 216kB/s]
+ 27%|##6 | 11.1M/41.5M [04:09<03:56, 135kB/s]
+ 27%|##6 | 11.2M/41.5M [04:09<03:05, 171kB/s]
+ 27%|##7 | 11.2M/41.5M [04:09<03:01, 175kB/s]
+ 27%|##7 | 11.3M/41.5M [04:09<02:28, 213kB/s]
+ 27%|##7 | 11.3M/41.5M [04:10<05:46, 91.3kB/s]
+ 27%|##7 | 11.4M/41.5M [04:11<04:05, 129kB/s]
+ 27%|##7 | 11.4M/41.5M [04:11<05:14, 100kB/s]
+ 28%|##7 | 11.4M/41.5M [04:12<07:10, 73.2kB/s]
+ 28%|##7 | 11.5M/41.5M [04:12<05:16, 99.5kB/s]
+ 28%|##7 | 11.5M/41.5M [04:12<05:40, 92.4kB/s]
+ 28%|##7 | 11.5M/41.5M [04:13<06:04, 86.2kB/s]
+ 28%|##7 | 11.5M/41.5M [04:13<08:01, 65.2kB/s]
+ 28%|##7 | 11.5M/41.5M [04:13<08:03, 65.0kB/s]
+ 28%|##7 | 11.5M/41.5M [04:14<08:04, 64.8kB/s]
+ 28%|##7 | 11.6M/41.5M [04:15<15:46, 33.2kB/s]
+ 28%|##7 | 11.6M/41.5M [04:15<18:17, 28.6kB/s]
+ 28%|##7 | 11.6M/41.5M [04:16<15:26, 33.8kB/s]
+ 28%|##7 | 11.6M/41.5M [04:16<13:28, 38.7kB/s]
+ 28%|##8 | 11.6M/41.5M [04:17<24:23, 21.4kB/s]
+ 28%|##8 | 11.6M/41.5M [04:18<25:16, 20.6kB/s]
+ 28%|##8 | 11.6M/41.5M [04:18<27:32, 18.9kB/s]
+ 28%|##8 | 11.6M/41.5M [04:19<28:07, 18.5kB/s]
+ 28%|##8 | 11.7M/41.5M [04:20<26:20, 19.8kB/s]
+ 28%|##8 | 11.7M/41.5M [04:21<38:17, 13.6kB/s]
+ 28%|##8 | 11.7M/41.5M [04:21<32:47, 15.9kB/s]
+ 28%|##8 | 11.7M/41.5M [04:22<32:43, 15.9kB/s]
+ 28%|##8 | 11.7M/41.5M [04:22<30:06, 17.3kB/s]
+ 28%|##8 | 11.7M/41.5M [04:22<24:54, 20.9kB/s]
+ 28%|##8 | 11.7M/41.5M [04:22<21:05, 24.7kB/s]
+ 28%|##8 | 11.7M/41.5M [04:23<18:20, 28.4kB/s]
+ 28%|##8 | 11.7M/41.5M [04:23<16:21, 31.8kB/s]
+ 28%|##8 | 11.7M/41.5M [04:23<14:56, 34.8kB/s]
+ 28%|##8 | 11.7M/41.5M [04:23<13:56, 37.3kB/s]
+ 28%|##8 | 11.7M/41.5M [04:23<13:13, 39.3kB/s]
+ 28%|##8 | 11.8M/41.5M [04:23<12:43, 40.8kB/s]
+ 28%|##8 | 11.8M/41.5M [04:24<12:22, 42.0kB/s]
+ 28%|##8 | 11.8M/41.5M [04:24<09:20, 55.6kB/s]
+ 28%|##8 | 11.8M/41.5M [04:24<09:52, 52.5kB/s]
+ 28%|##8 | 11.8M/41.5M [04:24<08:10, 63.5kB/s]
+ 28%|##8 | 11.8M/41.5M [04:24<07:17, 71.2kB/s]
+ 29%|##8 | 11.8M/41.5M [04:25<06:45, 76.7kB/s]
+ 29%|##8 | 11.8M/41.5M [04:25<07:41, 67.3kB/s]
+ 29%|##8 | 11.9M/41.5M [04:25<06:59, 74.0kB/s]
+ 29%|##8 | 11.9M/41.5M [04:25<06:34, 78.7kB/s]
+ 29%|##8 | 11.9M/41.5M [04:25<06:18, 82.1kB/s]
+ 29%|##8 | 11.9M/41.5M [04:25<06:07, 84.4kB/s]
+ 29%|##8 | 11.9M/41.5M [04:26<05:11, 99.5kB/s]
+ 29%|##8 | 11.9M/41.5M [04:26<05:20, 96.6kB/s]
+ 29%|##8 | 12.0M/41.5M [04:26<04:46, 108kB/s]
+ 29%|##8 | 12.0M/41.5M [04:26<03:58, 130kB/s]
+ 29%|##8 | 12.0M/41.5M [04:26<03:33, 145kB/s]
+ 29%|##9 | 12.1M/41.5M [04:27<03:18, 155kB/s]
+ 29%|##9 | 12.1M/41.5M [04:27<02:55, 176kB/s]
+ 29%|##9 | 12.1M/41.5M [04:27<02:30, 204kB/s]
+ 29%|##9 | 12.2M/41.5M [04:27<02:09, 237kB/s]
+ 30%|##9 | 12.2M/41.5M [04:27<01:57, 260kB/s]
+ 30%|##9 | 12.3M/41.5M [04:28<01:45, 290kB/s]
+ 30%|##9 | 12.4M/41.5M [04:28<01:34, 324kB/s]
+ 30%|### | 12.5M/41.5M [04:28<01:24, 362kB/s]
+ 30%|### | 12.5M/41.5M [04:28<01:15, 402kB/s]
+ 30%|### | 12.6M/41.5M [04:28<01:10, 430kB/s]
+ 31%|### | 12.7M/41.5M [04:28<01:03, 476kB/s]
+ 31%|### | 12.9M/41.5M [04:29<00:56, 535kB/s]
+ 31%|###1 | 13.0M/41.5M [04:29<00:50, 590kB/s]
+ 32%|###1 | 13.1M/41.5M [04:29<00:46, 642kB/s]
+ 32%|###1 | 13.3M/41.5M [04:29<00:41, 706kB/s]
+ 32%|###2 | 13.4M/41.5M [04:29<00:38, 764kB/s]
+ 33%|###2 | 13.6M/41.5M [04:30<00:35, 831kB/s]
+ 33%|###3 | 13.8M/41.5M [04:30<00:32, 905kB/s]
+ 34%|###3 | 14.0M/41.5M [04:30<00:29, 971kB/s]
+ 34%|###4 | 14.2M/41.5M [04:30<00:27, 1.06MB/s]
+ 35%|###4 | 14.4M/41.5M [04:30<00:25, 1.13MB/s]
+ 35%|###5 | 14.7M/41.5M [04:30<00:23, 1.22MB/s]
+ 36%|###5 | 14.9M/41.5M [04:31<00:21, 1.31MB/s]
+ 37%|###6 | 15.2M/41.5M [04:31<00:19, 1.41MB/s]
+ 37%|###7 | 15.5M/41.5M [04:31<00:18, 1.51MB/s]
+ 38%|###8 | 15.8M/41.5M [04:31<00:16, 1.61MB/s]
+ 39%|###8 | 16.2M/41.5M [04:31<00:15, 1.72MB/s]
+ 40%|###9 | 16.5M/41.5M [04:32<00:14, 1.84MB/s]
+ 41%|#### | 16.9M/41.5M [04:32<00:13, 1.93MB/s]
+ 42%|####1 | 17.3M/41.5M [04:32<00:12, 2.05MB/s]
+ 43%|####2 | 17.8M/41.5M [04:32<00:11, 2.18MB/s]
+ 44%|####3 | 18.2M/41.5M [04:32<00:10, 2.32MB/s]
+ 45%|####5 | 18.7M/41.5M [04:32<00:09, 2.47MB/s]
+ 46%|####6 | 19.2M/41.5M [04:33<00:08, 2.62MB/s]
+ 48%|####7 | 19.8M/41.5M [04:33<00:08, 2.77MB/s]
+ 49%|####9 | 20.3M/41.5M [04:33<00:07, 2.93MB/s]
+ 50%|##### | 20.9M/41.5M [04:33<00:06, 3.09MB/s]
+ 52%|#####2 | 21.6M/41.5M [04:33<00:06, 3.27MB/s]
+ 54%|#####3 | 22.2M/41.5M [04:34<00:05, 3.43MB/s]
+ 55%|#####5 | 23.0M/41.5M [04:34<00:05, 3.63MB/s]
+ 57%|#####7 | 23.7M/41.5M [04:34<00:04, 4.20MB/s]
+ 59%|#####8 | 24.4M/41.5M [04:34<00:03, 4.58MB/s]
+ 60%|###### | 24.9M/41.5M [04:34<00:03, 4.58MB/s]
+ 61%|######1 | 25.4M/41.5M [04:34<00:04, 3.92MB/s]
+ 63%|######3 | 26.2M/41.5M [04:34<00:03, 4.15MB/s]
+ 65%|######5 | 27.0M/41.5M [04:35<00:02, 5.24MB/s]
+ 67%|######7 | 27.8M/41.5M [04:35<00:02, 5.89MB/s]
+ 69%|######8 | 28.5M/41.5M [04:35<00:02, 5.16MB/s]
+ 70%|######9 | 29.0M/41.5M [04:35<00:02, 4.50MB/s]
+ 72%|#######2 | 30.0M/41.5M [04:35<00:02, 5.27MB/s]
+ 75%|#######4 | 31.0M/41.5M [04:35<00:01, 6.44MB/s]
+ 76%|#######6 | 31.6M/41.5M [04:35<00:01, 6.14MB/s]
+ 78%|#######7 | 32.3M/41.5M [04:36<00:01, 5.28MB/s]
+ 80%|######## | 33.3M/41.5M [04:36<00:01, 6.03MB/s]
+ 83%|########3 | 34.5M/41.5M [04:36<00:00, 7.37MB/s]
+ 85%|########4 | 35.2M/41.5M [04:36<00:00, 7.01MB/s]
+ 87%|########6 | 36.0M/41.5M [04:36<00:00, 6.01MB/s]
+ 89%|########9 | 37.1M/41.5M [04:36<00:00, 7.24MB/s]
+ 92%|#########2| 38.4M/41.5M [04:36<00:00, 8.48MB/s]
+ 95%|#########4| 39.2M/41.5M [04:36<00:00, 7.69MB/s]
+ 97%|#########6| 40.0M/41.5M [04:37<00:00, 6.62MB/s]
+100%|#########9| 41.4M/41.5M [04:37<00:00, 8.11MB/s]
+100%|##########| 41.5M/41.5M [04:37<00:00, 157kB/s]
</pre></div>
</div>
</div>
@@ -576,6 +1260,7 @@ 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> ( 5 minutes 1.922 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 064c456bb..826eb8dd5 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -464,7 +464,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 17.120 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 4.765 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 4da0ec28c..2c5d73ae7 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]
- 41%|#### | 18.2M/44.7M [00:00<00:00, 191MB/s]
- 96%|#########5| 42.8M/44.7M [00:00<00:00, 230MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 226MB/s]
+ 32%|###1 | 14.1M/44.7M [00:00<00:00, 148MB/s]
+ 79%|#######9 | 35.4M/44.7M [00:00<00:00, 192MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 194MB/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 4b550706f..2ccd2dc9d 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -607,7 +607,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.725 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 0.290 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 0d1c142f3..2c54437d7 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>05:34.942</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>09:45.416</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>01:17.120</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
-<li><p><strong>01:02.725</strong>: <a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></li>
-<li><p><strong>00:58.027</strong>: <a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></li>
-<li><p><strong>00:31.309</strong>: <a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></li>
-<li><p><strong>00:24.932</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
-<li><p><strong>00:22.362</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>00:21.784</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
-<li><p><strong>00:20.117</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
-<li><p><strong>00:13.761</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>00:02.806</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>05:01.922</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>01:04.765</strong>: <a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></li>
+<li><p><strong>01:00.290</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>00:56.720</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>00:24.256</strong>: <a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></li>
+<li><p><strong>00:21.236</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>00:21.104</strong>: <a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></li>
+<li><p><strong>00:19.170</strong>: <a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></li>
+<li><p><strong>00:13.492</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>00:02.460</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 a1dfb9fd5..3e315b41f 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -622,7 +622,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.8464 16.6414 17.4895 16.4227 0.3974
+ 15.9522 15.9067 16.2504 15.7817 0.1391
</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 103a9e743..6a01635ad 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 +409,24 @@ 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]
- 3%|2 | 4.47M/170M [00:00<00:03, 46.7MB/s]
- 5%|5 | 8.93M/170M [00:00<00:03, 44.9MB/s]
- 16%|#6 | 27.5M/170M [00:00<00:01, 111MB/s]
- 31%|###1 | 52.9M/170M [00:00<00:00, 172MB/s]
- 45%|####4 | 75.8M/170M [00:00<00:00, 196MB/s]
- 59%|#####8 | 99.4M/170M [00:00<00:00, 214MB/s]
- 72%|#######1 | 122M/170M [00:00<00:00, 221MB/s]
- 85%|########5 | 144M/170M [00:00<00:00, 226MB/s]
- 98%|#########8| 167M/170M [00:00<00:00, 227MB/s]
-100%|##########| 170M/170M [00:00<00:00, 193MB/s]
+ 1%|1 | 1.79M/170M [00:00<00:09, 18.7MB/s]
+ 2%|2 | 4.23M/170M [00:00<00:07, 22.7MB/s]
+ 9%|9 | 16.1M/170M [00:00<00:02, 69.0MB/s]
+ 17%|#6 | 28.1M/170M [00:00<00:01, 91.6MB/s]
+ 22%|##1 | 36.8M/170M [00:00<00:01, 90.0MB/s]
+ 28%|##7 | 47.5M/170M [00:00<00:01, 97.4MB/s]
+ 33%|###3 | 56.8M/170M [00:00<00:01, 94.9MB/s]
+ 39%|###9 | 66.7M/170M [00:00<00:01, 97.3MB/s]
+ 46%|####6 | 78.7M/170M [00:00<00:00, 106MB/s]
+ 53%|#####3 | 90.1M/170M [00:01<00:00, 110MB/s]
+ 59%|#####9 | 101M/170M [00:01<00:01, 69.2MB/s]
+ 64%|######4 | 109M/170M [00:01<00:01, 45.3MB/s]
+ 71%|#######1 | 121M/170M [00:01<00:00, 58.1MB/s]
+ 78%|#######8 | 133M/170M [00:01<00:00, 70.7MB/s]
+ 86%|########5 | 145M/170M [00:01<00:00, 82.6MB/s]
+ 93%|#########2| 157M/170M [00:02<00:00, 92.6MB/s]
+100%|#########9| 169M/170M [00:02<00:00, 101MB/s]
+100%|##########| 170M/170M [00:02<00:00, 80.8MB/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').
@@ -511,7 +519,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 13.089 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 3.865 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 1c55fda1a..88d9159a4 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, 177MB/s]
+ 15%|#4 | 2.02M/13.6M [00:00<00:00, 21.2MB/s]
+ 31%|### | 4.14M/13.6M [00:00<00:00, 21.7MB/s]
+ 48%|####8 | 6.53M/13.6M [00:00<00:00, 23.2MB/s]
+ 83%|########3 | 11.3M/13.6M [00:00<00:00, 33.5MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 32.0MB/s]
</pre></div>
</div>
</div>
@@ -539,7 +543,7 @@ 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)
- 90.6283 90.5904 92.5449 90.1969 0.3440
+ 90.2609 90.1858 91.2121 90.0475 0.2098
</pre></div>
</div>
<div class="admonition note">
@@ -578,7 +582,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.973 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.711 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 055a530b5..e4cc6da97 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -540,7 +540,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 119.1033 119.0934 121.1836 118.1825 0.4108
+ 121.0642 121.0349 125.7071 120.1228 0.6102
</pre></div>
</div>
<div class="admonition note">
@@ -568,7 +568,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 0.665 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 57.369 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 55185cb94..3fa772a9d 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -480,7 +480,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.247 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 2.941 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 b467c7d1f..0191edd3c 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -415,24 +415,23 @@ 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]
- 3%|3 | 4009/132723 [00:00<00:03, 40075.61KB/s]
- 8%|8 | 11230/132723 [00:00<00:02, 58971.88KB/s]
- 14%|#4 | 18953/132723 [00:00<00:01, 67302.73KB/s]
- 20%|## | 26701/132723 [00:00<00:01, 71317.15KB/s]
- 26%|##6 | 34664/132723 [00:00<00:01, 74313.33KB/s]
- 32%|###2 | 42671/132723 [00:00<00:01, 76265.96KB/s]
- 38%|###8 | 50724/132723 [00:00<00:01, 77658.00KB/s]
- 44%|####4 | 58840/132723 [00:00<00:00, 78768.32KB/s]
- 50%|##### | 66903/132723 [00:00<00:00, 79338.34KB/s]
- 57%|#####6 | 75041/132723 [00:01<00:00, 79965.67KB/s]
- 63%|######2 | 83121/132723 [00:01<00:00, 80219.95KB/s]
- 69%|######8 | 91271/132723 [00:01<00:00, 80608.23KB/s]
- 75%|#######4 | 99343/132723 [00:01<00:00, 80640.89KB/s]
- 81%|######## | 107479/132723 [00:01<00:00, 80851.41KB/s]
- 87%|########7 | 115565/132723 [00:01<00:00, 80741.23KB/s]
- 93%|#########3| 123643/132723 [00:01<00:00, 80751.81KB/s]
- 99%|#########9| 131719/132723 [00:01<00:00, 80519.12KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 77383.60KB/s]
+ 5%|4 | 6565/132723 [00:00<00:01, 65636.45KB/s]
+ 11%|# | 14591/132723 [00:00<00:01, 74234.52KB/s]
+ 17%|#7 | 22822/132723 [00:00<00:01, 77918.59KB/s]
+ 23%|##3 | 30859/132723 [00:00<00:01, 78882.71KB/s]
+ 29%|##9 | 38933/132723 [00:00<00:01, 79547.86KB/s]
+ 35%|###5 | 46970/132723 [00:00<00:01, 79824.67KB/s]
+ 41%|####1 | 55029/132723 [00:00<00:00, 80073.51KB/s]
+ 48%|####7 | 63090/132723 [00:00<00:00, 80242.61KB/s]
+ 54%|#####3 | 71179/132723 [00:00<00:00, 80442.37KB/s]
+ 60%|#####9 | 79256/132723 [00:01<00:00, 80542.46KB/s]
+ 66%|######5 | 87311/132723 [00:01<00:00, 80510.43KB/s]
+ 72%|#######1 | 95413/132723 [00:01<00:00, 80662.96KB/s]
+ 78%|#######8 | 103563/132723 [00:01<00:00, 80914.39KB/s]
+ 84%|########4 | 111718/132723 [00:01<00:00, 81104.43KB/s]
+ 90%|######### | 119829/132723 [00:01<00:00, 81018.28KB/s]
+ 96%|#########6| 127977/132723 [00:01<00:00, 81153.79KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 80005.35KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -472,7 +471,7 @@ 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 25.184 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 22.448 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 3e556e993..31167a2b4 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>10:54.397</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>11:22.976</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<ul class="simple">
-<li><p><strong>03:13.089</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>02:25.184</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>02:00.665</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>01:14.247</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>01:07.973</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>00:29.936</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>00:23.097</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>00:00.206</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>03:03.865</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>02:22.448</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>02:02.941</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>01:57.369</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>01:05.711</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>00:28.311</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>00:22.133</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>00:00.200</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 98f6576d6..43914dded 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -588,7 +588,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc6017630-3622-447b-bdaf-b8f11e17ab66 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.zipaf4c81c7-6904-47fb-bed2-21df8c378cec 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 04b30f223..6e2bf0cd2 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>00:38.346</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:37.991</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:34.784</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>00:02.281</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>00:01.070</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>00:00.211</strong>: <a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></li>
+<li><p><strong>00:34.419</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>00:02.280</strong>: <a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></li>
+<li><p><strong>00:01.084</strong>: <a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></li>
+<li><p><strong>00:00.208</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>
</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 148069628..b61336a8c 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: 5982us [5982us] (45.30%; 45.30%)
-FoldScaleAxis: 7221us [2us] (54.70%; 54.70%)
- FoldConstant: 7219us [1503us] (54.68%; 99.97%)
- InferType: 5717us [5717us] (43.30%; 79.18%)
+InferType: 6298us [6298us] (35.30%; 35.30%)
+FoldScaleAxis: 11541us [2us] (64.70%; 64.70%)
+ FoldConstant: 11538us [1555us] (64.68%; 99.98%)
+ InferType: 9983us [9983us] (55.97%; 86.52%)
</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: 5790us [5790us] (44.67%; 44.67%)
-FoldScaleAxis: 7171us [2us] (55.33%; 55.33%)
- FoldConstant: 7169us [1501us] (55.31%; 99.98%)
- InferType: 5668us [5668us] (43.73%; 79.06%)
+InferType: 6051us [6051us] (44.23%; 44.23%)
+FoldScaleAxis: 7630us [2us] (55.77%; 55.77%)
+ FoldConstant: 7628us [1557us] (55.76%; 99.97%)
+ InferType: 6070us [6070us] (44.37%; 79.59%)
</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 34aeb43cc..183bbf3f5 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: 44.960085 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 40.847642 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 39e3499c4..511bc4ac4 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -878,7 +878,7 @@ be able to run on our build server</p>
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.575889 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 10.216524 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 4b565512c..1fdf978e8 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: 0.018374
-Baseline: 3.430116
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018140
+Baseline: 3.335576
</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: 0.305009
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.300501
</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: 0.345004
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.336995
</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: 0.115727
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.115701
</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: 0.110674
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110963
</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: 0.112359
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111396
</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: 0.145375
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.144963
</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 b09eba094..63eba576a 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -300,11 +300,11 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.286</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.767</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:32.578</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>00:01.470</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>00:01.238</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>00:32.101</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>00:01.432</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>00:01.234</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 bb5d53453..1ccdfa5a1 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -300,14 +300,14 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:02.483</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:11.563</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<ul class="simple">
-<li><p><strong>02:27.689</strong>: <a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></li>
-<li><p><strong>01:19.442</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
-<li><p><strong>00:40.751</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>00:17.098</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>00:08.908</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>00:08.594</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>02:36.850</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>01:18.838</strong>: <a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></li>
+<li><p><strong>00:40.225</strong>: <a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></li>
+<li><p><strong>00:18.519</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>00:08.742</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>00:08.390</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 cdc5aa724..05b65fa30 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
@@ -450,7 +450,7 @@ file and apply it.</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>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
</pre></div>
</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
@@ -470,333 +470,698 @@ 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, [2]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [2], [], scope="local", align=8)[0] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [14]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [108]), 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" = 16 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [49], [], scope="local", align=16)[0] = 0f32
+ conv2d_nchw_1[7] = 0f32
conv2d_nchw_1[1] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_2: int32 = (rc.outer.outer*784)
- let cse_var_1: int32 = (rc.outer.outer*144)
+ conv2d_nchw_1[8] = 0f32
+ conv2d_nchw_1[2] = 0f32
+ conv2d_nchw_1[9] = 0f32
+ conv2d_nchw_1[3] = 0f32
+ conv2d_nchw_1[10] = 0f32
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[11] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[12] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ conv2d_nchw_1[13] = 0f32
+ for (rc.outer.outer: int32, 0, 128) {
+ let cse_var_2: int32 = (rc.outer.outer*196)
+ let cse_var_1: int32 = (rc.outer.outer*36)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((9 <= floormod(threadIdx.x_1, 81)) && (floormod(threadIdx.x_1, 81) < 72)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 81)*49)) + (floordiv(floormod(threadIdx.x_1, 81), 9)*7)) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- 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" = 392;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 784), 81)) && (floormod((threadIdx.x_1 + 55), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 784), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 784), 81), 9)*7)) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_1 < 120), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1 + 1176), 81)) && (floormod((threadIdx.x_1 + 42), 81) < 72)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_2 + (floordiv((threadIdx.x_1 + 1176), 81)*49)) + (floordiv(floormod((threadIdx.x_1 + 1176), 81), 9)*7)) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [108], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else((((3 <= threadIdx.x_1) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((cse_var_2 + (floordiv(threadIdx.x_1, 3)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 16)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 16), 27)) && (floormod((threadIdx.x_1 + 16), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 16), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 16), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 32)] = @tir.if_then_else(((1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 32), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 32), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 2), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 48)] = @tir.if_then_else(((((1 <= floormod((floordiv(threadIdx.x_1, 3) + 7), 9)) && (floormod((threadIdx.x_1 + 21), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 48), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 7), 9)*7)) + floormod(blockIdx.x, 7)) + floormod( [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 64)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 10), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 1), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 64), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 64), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_1 + 1), 3)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ pad_temp.shared_1[(threadIdx.x_1 + 80)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 80), 27)) && (floormod((threadIdx.x_1 + 26), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 80), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 80), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floorm [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ if @tir.likely((threadIdx.x_1 < 12), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 96)] = @tir.if_then_else((((floormod((threadIdx.x_1 + 15), 27) < 24) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[(((((cse_var_2 + (floordiv((threadIdx.x_1 + 96), 27)*49)) + (floormod((floordiv(threadIdx.x_1, 3) + 5), 9)*7)) + floormod(blockIdx.x, 7)) + floormod(threadIdx.x_1, 3)) - 8)], 0f32, dtype=float32)
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[threadIdx.x_2] = kernel[((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 144)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 49), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 104), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 98), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 64), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 147), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 196), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 128), 144))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 392;
- if @tir.likely((threadIdx.x_2 < 344), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((blockIdx.x*73728) + (floordiv((floordiv(threadIdx.x_2, 8) + 245), 18)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 88), 144))]
- }
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[(floordiv(threadIdx.x, 49)*288)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7))]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 144)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 3)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 147)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 6)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 150)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 9)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 81)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 153)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 12)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 90)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 156)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 15)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 99)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 159)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 18)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 162)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 162)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 21)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 171)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 165)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 24)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 180)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 168)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 27)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 243)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 171)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 30)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 252)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 174)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 33)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 261)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 177)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 1)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 145)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 4)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 148)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 7)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 151)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 10)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 82)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 154)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 13)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 91)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 157)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 16)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 100)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 160)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 19)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 163)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 163)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 22)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 172)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 166)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 25)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 181)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 169)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 28)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 244)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 172)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 31)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 253)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 175)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 34)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 262)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 178)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 2)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 146)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 5)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 149)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 8)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 152)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 11)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 83)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 155)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 14)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 92)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 158)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 17)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 101)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 161)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 20)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 164)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 164)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 23)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 173)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 167)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 26)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 182)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 170)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 29)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 245)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 173)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 32)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 254)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 176)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 35)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 263)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 179)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 36)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 324)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 180)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 39)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 333)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 183)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 42)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 342)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 186)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 45)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 405)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 189)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 48)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 414)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 192)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 51)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 423)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 195)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 54)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 486)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 198)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 57)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 495)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 201)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 60)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 504)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 204)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 63)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 567)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 207)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 66)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 576)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 210)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 69)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 585)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 213)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 37)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 325)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 181)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 40)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 334)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 184)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 43)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 343)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 187)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 46)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 406)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 190)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 49)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 415)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 193)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 52)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 424)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 196)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 55)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 487)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 199)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 58)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 496)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 202)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 61)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 505)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 205)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 64)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 568)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 208)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 67)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 577)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 211)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 70)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 586)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 214)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 38)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 326)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 182)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 41)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 335)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 185)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 44)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 344)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 188)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 47)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 407)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 191)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 50)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 416)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 194)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 53)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 425)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 197)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 56)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 488)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 200)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 59)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 497)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 203)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 62)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 506)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 206)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 65)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 569)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 209)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 68)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 578)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 212)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 71)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 587)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 215)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 72)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 648)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 216)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 75)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 657)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 219)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 78)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 666)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 222)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 81)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 729)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 225)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 84)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 738)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 228)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 87)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 747)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 231)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 90)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 810)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 234)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 93)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 819)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 237)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 96)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 828)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 240)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 99)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 891)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 243)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 102)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 900)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 246)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 105)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 909)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 249)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 73)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 649)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 217)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 76)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 658)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 220)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 79)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 667)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 223)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 82)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 730)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 226)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 85)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 739)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 229)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 88)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 748)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 232)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 91)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 811)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 235)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 94)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 820)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 238)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 97)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 829)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 241)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 100)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 892)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 244)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 103)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 901)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 247)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 106)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 910)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 250)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 74)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 650)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 218)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 77)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 659)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 221)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 80)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 668)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 224)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 83)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 731)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 227)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 86)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 740)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 230)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 89)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 749)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 233)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 92)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 812)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 236)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 95)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 821)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 239)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 98)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 830)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 242)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 101)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 893)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 245)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 104)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 902)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 248)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 107)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 911)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 251)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 108)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 972)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 252)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 111)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 981)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 255)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 114)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 990)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 258)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 117)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1053)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 261)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 120)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1062)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 264)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 123)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1071)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 267)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 126)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1134)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 270)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 129)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1143)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 273)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 132)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1152)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 276)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 135)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1215)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 279)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 138)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1224)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 282)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 141)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1233)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 285)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 109)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 973)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 253)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 112)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 982)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 256)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 115)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 991)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 259)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 118)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1054)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 262)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 121)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1063)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 265)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 124)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1072)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 268)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 127)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1135)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 271)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 130)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1144)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 274)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 133)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1153)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 277)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 136)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1216)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 280)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 139)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1225)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 283)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 142)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1234)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 286)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 110)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 974)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 254)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 113)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 983)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 257)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 116)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 992)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 260)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 119)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1055)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 263)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 122)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1064)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 266)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 125)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1073)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 269)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 128)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1136)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 272)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 131)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1145)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 275)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 134)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1154)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 278)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 137)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1217)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 281)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 140)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1226)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 284)]))
- conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 143)]))
- conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[(((floordiv(floormod(threadIdx.x, 49), 7)*9) + floormod(threadIdx.x, 7)) + 1235)]*kernel.shared_1[((floordiv(threadIdx.x, 49)*288) + 287)]))
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1: Buffer(kernel.shared, float32, [1152], [], scope="shared")[threadIdx.x_2] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 16)] = kernel[(((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + (threadIdx.x_2 + 16))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 8), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 48)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 12), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 16), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 80)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 20), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 24), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 112)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 28), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 32), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 144)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 40), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 176)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 44), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 48), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 208)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 52), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 56), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 240)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 60), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 64), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 272)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 68), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 304)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 76), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 80), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 336)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 84), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 88), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 368)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 92), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 96), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 400)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 100), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 104), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 432)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 112), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 464)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 116), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 120), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 496)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 124), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 128), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 528)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 132), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 136), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 560)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 140), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 592)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 148), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 152), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 624)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 156), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 160), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 656)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 164), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 168), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 688)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 172), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 176), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 720)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 184), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 752)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 188), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 192), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 200), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 816)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 204), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 208), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 848)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 212), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 880)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 220), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 224), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 912)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 228), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 232), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 944)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 236), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 240), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 976)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 244), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 248), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1008)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + cse_var_1) + threadIdx.x_2) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 256), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 16), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1040)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 260), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 32), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 264), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 12), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1072)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 268), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 28), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 272), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 8), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1104)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 276), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 24), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 280), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 4), 36))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 16;
+ kernel.shared_1[(threadIdx.x_2 + 1136)] = kernel[((((floordiv(blockIdx.x, 7)*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 284), 9)*4608)) + cse_var_1) + floormod((threadIdx.x_2 + 20), 36))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[0]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*36)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*36) + 576)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 1)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*36) + 577)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 2)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*36) + 578)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 3)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*36) + 579)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 4)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*36) + 580)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 5)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*36) + 581)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 6)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*36) + 582)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 7)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*36) + 583)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 8)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*36) + 584)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 9)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*36) + 585)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 10)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*36) + 586)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 11)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*36) + 587)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 12)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*36) + 588)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 13)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*36) + 589)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 14)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*36) + 590)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 15)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*36) + 591)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 16)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*36) + 592)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 17)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*36) + 593)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 18)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*36) + 594)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 19)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*36) + 595)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 20)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*36) + 596)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 21)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*36) + 597)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 22)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*36) + 598)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 23)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*36) + 599)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 24)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*36) + 600)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 25)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*36) + 601)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 26)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*36) + 602)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[7] = (conv2d_nchw_1[7] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[8] = (conv2d_nchw_1[8] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[9] = (conv2d_nchw_1[9] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[10] = (conv2d_nchw_1[10] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[11] = (conv2d_nchw_1[11] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[12] = (conv2d_nchw_1[12] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 611)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 27)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*36) + 603)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 28)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*36) + 604)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 29)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*36) + 605)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 30)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*36) + 606)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 31)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*36) + 607)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 32)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*36) + 608)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 33)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*36) + 609)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 34)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*36) + 610)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 35)]))
+ conv2d_nchw_1[13] = (conv2d_nchw_1[13] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*36) + 611)]))
}
}
- for (i1.inner: int32, 0, 2) {
- compute[((((blockIdx.x*784) + (floordiv(threadIdx.x, 49)*98)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*16) + (floordiv(threadIdx.x, 49)*2)) + i1.inner)]), 0f32)
+ for (i2.inner: int32, 0, 7) {
+ compute[((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[i2.inner] + bias[((floordiv(blockIdx.x, 7)*32) + threadIdx.x)]), 0f32)
+ compute[(((((floordiv(blockIdx.x, 7)*1568) + (threadIdx.x*49)) + (i2.inner*7)) + floormod(blockIdx.x, 7)) + 784)] = max((conv2d_nchw_1[(i2.inner + 7)] + bias[(((floordiv(blockIdx.x, 7)*32) + threadIdx.x) + 16)]), 0f32)
}
}
}
@@ -834,7 +1199,7 @@ 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: 0.300 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.332 ms
</pre></div>
</div>
</div>
@@ -864,36 +1229,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
+conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=1)
conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=1)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=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_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=16)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=2)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
-conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
+conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=7)
+conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=1)
conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
conv2d_nchw_xx_o_i, conv2d_nchw_xx_i = s[conv2d_nchw].split(conv2d_nchw_xx, factor=1)
conv2d_nchw_xx_o_o_i, conv2d_nchw_xx_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_i, factor=1)
-conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=7)
+conv2d_nchw_xx_o_o_o_i, conv2d_nchw_xx_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_i, factor=1)
conv2d_nchw_xx_o_o_o_o, conv2d_nchw_xx_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_xx_o_o_o_i, factor=1)
-conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=4)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=1)
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=3)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=1)
-conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=3)
+conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=3)
+conv2d_nchw_rx_o_o, conv2d_nchw_rx_o_i = s[conv2d_nchw].split(conv2d_nchw_rx_o_i, factor=1)
s[conv2d_nchw].reorder(conv2d_nchw_nn_o_o_o_o, conv2d_nchw_ff_o_o_o_o, conv2d_nchw_yy_o_o_o_o, conv2d_nchw_xx_o_o_o_o, conv2d_nchw_nn_o_o_o_i, conv2d_nchw_ff_o_o_o_i, conv2d_nchw_yy_o_o_o_i, conv2d_nchw_xx_o_o_o_i, conv2d_nchw_nn_o_o_i, conv2d_nchw_ff_o_o_i, conv2d_nchw_yy_o_o_i, conv2d_nchw_xx_o_o_i, conv2d_nchw_rc_o_o, conv2d_nchw_ry_o_o, conv2d_nchw_rx_o_o, conv2d_nchw_rc_o_i, conv2d_nchw_ry_o_i, conv2d_nchw_rx_o_i, conv2d_nchw_nn_o_i, conv2d_nchw_ff_o_i, conv2d_nchw_yy_o_i, conv2d_nc [...]
compute_i0_o_i, compute_i0_i = s[compute].split(compute_i0, factor=1)
compute_i0_o_o_i, compute_i0_o_i = s[compute].split(compute_i0_o_i, factor=1)
compute_i0_o_o_o, compute_i0_o_o_i = s[compute].split(compute_i0_o_o_i, factor=1)
-compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=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=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+compute_i1_o_i, compute_i1_i = s[compute].split(compute_i1, factor=1)
+compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=16)
+compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=2)
+compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=7)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
compute_i3_o_i, compute_i3_i = s[compute].split(compute_i3, factor=1)
-compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=7)
+compute_i3_o_o_i, compute_i3_o_i = s[compute].split(compute_i3_o_i, factor=1)
compute_i3_o_o_o, compute_i3_o_o_i = s[compute].split(compute_i3_o_o_i, factor=1)
s[compute].reorder(compute_i0_o_o_o, compute_i1_o_o_o, compute_i2_o_o_o, compute_i3_o_o_o, compute_i0_o_o_i, compute_i1_o_o_i, compute_i2_o_o_i, compute_i3_o_o_i, compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i, compute_i0_i, compute_i1_i, compute_i2_i, compute_i3_i)
s[conv2d_nchw].compute_at(s[compute], compute_i3_o_i)
@@ -913,12 +1278,12 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=392)
+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=16)
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=392)
+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=16)
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, "unroll_explicit", True)
@@ -938,320 +1303,616 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(392) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[2];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(16) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[14];
+ __shared__ float pad_temp_shared[108];
+ __shared__ float kernel_shared[1152];
conv2d_nchw[0] = 0.000000e+00f;
+ conv2d_nchw[7] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[8] = 0.000000e+00f;
+ conv2d_nchw[2] = 0.000000e+00f;
+ conv2d_nchw[9] = 0.000000e+00f;
+ conv2d_nchw[3] = 0.000000e+00f;
+ conv2d_nchw[10] = 0.000000e+00f;
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[11] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[12] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ conv2d_nchw[13] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 128; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((9 <= (((int)threadIdx.x) % 81)) && ((((int)threadIdx.x) % 81) < 72)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((int)threadIdx.x) / 81) * 49)) + (((((int)threadIdx.x) % 81) / 9) * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((9 <= ((((int)threadIdx.x) + 68) % 81)) && (((((int)threadIdx.x) + 68) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 392) / 81) * 49)) + ((((((int)threadIdx.x) + 68) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((9 <= ((((int)threadIdx.x) + 55) % 81)) && (((((int)threadIdx.x) + 55) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 784) / 81) * 49)) + ((((((int)threadIdx.x) + 55) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 120) {
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((9 <= ((((int)threadIdx.x) + 42) % 81)) && (((((int)threadIdx.x) + 42) % 81) < 72)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) + 1176) / 81) * 49)) + ((((((int)threadIdx.x) + 42) % 81) / 9) * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 144) * 4608)) + (rc_outer_outer * 144)) + (((int)threadIdx.x) % 144))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 392) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 104) % 144))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 784) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 64) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1176) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 24) % 144))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1568) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 128) % 144))];
- if (((int)threadIdx.x) < 344) {
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 1960) / 144) * 4608)) + (rc_outer_outer * 144)) + ((((int)threadIdx.x) + 88) % 144))];
+ pad_temp_shared[((int)threadIdx.x)] = ((((3 <= ((int)threadIdx.x)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[(((((rc_outer_outer * 196) + ((((int)threadIdx.x) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 16)] = (((((3 <= ((((int)threadIdx.x) + 16) % 27)) && (((((int)threadIdx.x) + 16) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 16) / 27) * 49)) + ((((((int)threadIdx.x) + 16) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) [...]
+ pad_temp_shared[(((int)threadIdx.x) + 32)] = (((1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 32) / 27) * 49)) + ((((((int)threadIdx.x) + 5) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 48)] = (((((1 <= (((((int)threadIdx.x) / 3) + 7) % 9)) && (((((int)threadIdx.x) + 21) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 48) / 27) * 49)) + ((((((int)threadIdx.x) / 3) + 7) % 9) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0 [...]
+ pad_temp_shared[(((int)threadIdx.x) + 64)] = ((((((int)threadIdx.x) < 14) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 64) / 27) * 49)) + ((((((int)threadIdx.x) + 10) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 1) % 3)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) + 80)] = (((((3 <= ((((int)threadIdx.x) + 26) % 27)) && (((((int)threadIdx.x) + 26) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 80) / 27) * 49)) + ((((((int)threadIdx.x) + 26) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) [...]
+ if (((int)threadIdx.x) < 12) {
+ pad_temp_shared[(((int)threadIdx.x) + 96)] = ((((((int)threadIdx.x) < 9) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 196) + (((((int)threadIdx.x) + 96) / 27) * 49)) + (((((int)threadIdx.x) / 3) + 5) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x))];
+ kernel_shared[(((int)threadIdx.x) + 16)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 16)];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 32) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 48)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 48) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 64) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 80)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 80) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 96) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 112)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 112) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 128) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 144)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 160) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 176)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 176) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 192) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 208)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 208) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 224) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 240)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 240) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 256) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 272)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 272) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 304)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 304) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 320) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 336)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 336) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 352) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 368)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 368) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 384) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 400)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 400) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 416) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 432)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 448) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 464)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 464) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 480) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 496)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 496) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 512) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 528)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 528) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 544) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 560)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 560) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 592)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 592) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 608) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 624)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 624) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 640) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 656)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 656) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 672) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 688)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 688) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 704) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 720)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 736) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 752)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 752) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 768) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 784)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 784) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 800) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 816)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 816) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 832) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 848)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 848) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 880)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 880) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 896) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 912)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 912) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 928) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 944)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 944) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 960) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 976)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 976) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 992) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
+ kernel_shared[(((int)threadIdx.x) + 1008)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 36)) + ((int)threadIdx.x)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1024) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 16))];
+ kernel_shared[(((int)threadIdx.x) + 1040)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1040) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 32) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1056) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 12))];
+ kernel_shared[(((int)threadIdx.x) + 1072)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1072) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 28) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1088) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 8))];
+ kernel_shared[(((int)threadIdx.x) + 1104)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1104) / 36) * 4608)) + (rc_outer_outer * 36)) + ((((int)threadIdx.x) + 24) % 36))];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1120) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 4))];
+ kernel_shared[(((int)threadIdx.x) + 1136)] = kernel[(((((((int)blockIdx.x) / 7) * 147456) + (((((int)threadIdx.x) + 1136) / 36) * 4608)) + (rc_outer_outer * 36)) + (((int)threadIdx.x) + 20))];
__syncthreads();
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[((((int)threadIdx.x) / 49) * 288)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 144)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 3)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 147)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 6)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 150)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 9)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 81)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 153)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 12)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 90)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 156)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 15)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 99)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 159)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 18)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 162)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 162)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 21)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 171)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 165)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 24)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 180)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 168)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 27)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 243)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 171)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 30)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 252)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 174)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 33)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 261)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 177)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 1)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 145)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 4)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 148)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 7)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 151)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 10)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 82)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 154)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 13)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 91)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 157)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 16)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 100)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 160)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 19)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 163)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 163)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 22)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 172)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 166)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 25)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 181)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 169)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 28)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 244)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 172)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 31)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 253)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 175)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 34)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 262)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 178)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 2)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 146)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 5)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 149)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 8)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 152)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 11)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 83)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 155)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 14)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 92)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 158)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 17)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 101)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 161)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 20)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 164)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 164)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 23)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 173)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 167)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 26)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 182)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 170)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 29)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 245)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 173)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 32)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 254)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 176)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 35)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 263)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 179)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 36)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 324)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 180)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 39)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 333)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 183)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 42)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 342)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 186)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 45)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 405)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 189)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 48)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 414)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 192)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 51)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 423)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 195)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 54)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 486)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 198)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 57)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 495)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 201)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 60)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 504)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 204)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 63)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 567)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 207)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 66)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 576)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 210)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 69)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 585)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 213)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 37)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 325)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 181)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 40)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 334)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 184)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 43)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 343)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 187)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 46)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 406)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 190)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 49)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 415)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 193)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 52)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 424)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 196)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 55)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 487)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 199)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 58)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 496)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 202)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 61)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 505)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 205)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 64)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 568)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 208)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 67)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 577)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 211)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 70)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 586)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 214)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 38)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 326)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 182)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 41)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 335)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 185)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 44)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 344)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 188)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 47)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 407)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 191)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 50)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 416)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 194)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 53)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 425)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 197)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 56)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 488)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 200)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 59)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 497)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 203)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 62)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 506)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 206)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 65)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 569)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 209)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 68)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 578)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 212)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 71)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 587)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 215)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 72)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 648)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 216)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 75)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 657)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 219)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 78)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 666)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 222)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 81)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 729)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 225)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 84)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 738)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 228)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 87)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 747)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 231)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 90)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 810)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 234)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 93)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 819)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 237)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 96)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 828)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 240)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 99)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 891)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 243)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 102)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 900)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 246)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 105)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 909)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 249)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 73)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 649)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 217)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 76)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 658)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 220)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 79)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 667)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 223)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 82)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 730)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 226)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 85)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 739)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 229)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 88)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 748)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 232)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 91)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 811)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 235)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 94)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 820)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 238)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 97)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 829)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 241)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 100)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 892)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 244)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 103)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 901)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 247)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 106)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 910)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 250)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 74)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 650)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 218)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 77)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 659)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 221)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 80)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 668)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 224)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 83)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 731)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 227)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 86)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 740)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 230)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 89)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 749)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 233)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 92)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 812)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 236)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 95)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 821)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 239)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 98)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 830)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 242)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 101)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 893)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 245)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 104)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 902)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 248)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 107)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 911)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 251)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 108)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 972)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 252)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 111)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 981)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 255)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 114)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 990)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 258)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 117)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1053)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 261)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 120)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1062)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 264)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 123)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1071)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 267)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 126)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1134)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 270)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 129)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1143)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 273)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 132)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1152)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 276)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 135)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1215)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 279)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 138)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1224)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 282)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 141)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1233)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 285)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 109)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 973)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 253)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 112)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 982)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 256)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 115)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 991)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 259)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 118)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1054)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 262)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 121)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1063)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 265)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 124)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1072)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 268)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 127)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1135)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 271)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 130)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1144)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 274)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 133)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1153)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 277)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 136)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1216)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 280)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 139)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1225)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 283)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 142)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1234)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 286)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 110)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 974)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 254)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 113)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 983)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 257)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 116)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 992)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 260)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 119)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1055)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 263)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 122)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1064)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 266)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 125)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1073)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 269)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 128)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1136)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 272)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 131)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1145)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 275)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 134)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1154)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 278)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 137)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1217)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 281)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 140)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1226)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 284)]));
- conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 143)]));
- conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[(((((((int)threadIdx.x) % 49) / 7) * 9) + (((int)threadIdx.x) % 7)) + 1235)] * kernel_shared[(((((int)threadIdx.x) / 49) * 288) + 287)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[0] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 36)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 36) + 576)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 1)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 36) + 577)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 2)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 36) + 578)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 3)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 36) + 579)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 4)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 36) + 580)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 5)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 36) + 581)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 6)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 36) + 582)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 7)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 36) + 583)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 8)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 36) + 584)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 9)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 36) + 585)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 10)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 36) + 586)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 11)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 36) + 587)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 12)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 36) + 588)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 13)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 36) + 589)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 14)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 36) + 590)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 15)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 36) + 591)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 16)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 36) + 592)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 17)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 36) + 593)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 18)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 36) + 594)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 19)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 36) + 595)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 20)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 36) + 596)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 21)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 36) + 597)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 22)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 36) + 598)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 23)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 36) + 599)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 24)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 36) + 600)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 25)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 36) + 601)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 26)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 36) + 602)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[7] = (conv2d_nchw[7] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[8] = (conv2d_nchw[8] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[9] = (conv2d_nchw[9] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[10] = (conv2d_nchw[10] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[11] = (conv2d_nchw[11] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[12] = (conv2d_nchw[12] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 27)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 36) + 603)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 28)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 36) + 604)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 29)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 36) + 605)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 30)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 36) + 606)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 31)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 36) + 607)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 32)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 36) + 608)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 33)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 36) + 609)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 34)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 36) + 610)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 35)]));
+ conv2d_nchw[13] = (conv2d_nchw[13] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 36) + 611)]));
}
- for (int i1_inner = 0; i1_inner < 2; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 784) + ((((int)threadIdx.x) / 49) * 98)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 16) + ((((int)threadIdx.x) / 49) * 2)) + i1_inner)]), 0.000000e+00f);
+ for (int i2_inner = 0; i2_inner < 7; ++i2_inner) {
+ compute[(((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[i2_inner] + bias[(((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[((((((((int)blockIdx.x) / 7) * 1568) + (((int)threadIdx.x) * 49)) + (i2_inner * 7)) + (((int)blockIdx.x) % 7)) + 784)] = max((conv2d_nchw[(i2_inner + 7)] + bias[((((((int)blockIdx.x) / 7) * 32) + ((int)threadIdx.x)) + 16)]), 0.000000e+00f);
}
}
</pre></div>
@@ -1289,7 +1950,7 @@ In the example below we resume the status and do more 5 trials.</p>
Get devices for measurement successfully!
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 27.689 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.850 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 8ce6ab9fd..a8911965a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -876,7 +876,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.7327 9.7499 9.7608 9.6874 0.0323
+ 9.9808 9.9960 10.0422 9.9044 0.0573
</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 74435625e..82e5af3f6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -895,7 +895,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 776.9521 778.1767 785.8943 766.7854 7.8491
+ 758.6640 761.3320 762.2156 752.4443 4.4127
</pre></div>
</div>
</div>
@@ -917,7 +917,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.442 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 18.838 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 4a27e3979..785e438ab 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -600,74 +600,28 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_7: placeholder_15: Buffer(placeholder_12, int32, [4916], []), placeholder_9: placeholder_16: Buffer(placeholder_14, float32, [128, 512], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_5: placeholder_18: Buffer(placeholder_10, float32, [128, 256], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 2) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global;
- for (i1.outer: int32, 0, 32) {
- for (i.inner.init: int32, 0, 64) {
- let cse_var_1: int32 = (i.inner.init*16)
- {
- compute_5: Buffer(compute_4, float32, [1024], [])[cse_var_1] = 0f32
- compute_5[(cse_var_1 + 1)] = 0f32
- compute_5[(cse_var_1 + 2)] = 0f32
- compute_5[(cse_var_1 + 3)] = 0f32
- compute_5[(cse_var_1 + 4)] = 0f32
- compute_5[(cse_var_1 + 5)] = 0f32
- compute_5[(cse_var_1 + 6)] = 0f32
- compute_5[(cse_var_1 + 7)] = 0f32
- compute_5[(cse_var_1 + 8)] = 0f32
- compute_5[(cse_var_1 + 9)] = 0f32
- compute_5[(cse_var_1 + 10)] = 0f32
- compute_5[(cse_var_1 + 11)] = 0f32
- compute_5[(cse_var_1 + 12)] = 0f32
- compute_5[(cse_var_1 + 13)] = 0f32
- compute_5[(cse_var_1 + 14)] = 0f32
- compute_5[(cse_var_1 + 15)] = 0f32
+ preflattened_buffer_map = {placeholder_9: placeholder_15: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_16: Buffer(placeholder_11, float32, [4916, 16, 1], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_18: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_19: Buffer(placeholder_13, int32, [33], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 128) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [512]), storage_scope = global {
+ for (i.outer.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 16) {
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [512], [])[(((i.outer.inner*256) + (i.inner.init*16)) + j.init)] = 0f32
+ }
}
- }
- for (elem_idx: int32, 0, (placeholder_3[(i1.outer + 1)] - placeholder_3[i1.outer])) {
- for (i.inner: int32, 0, 64) {
- let cse_var_19: int32 = (i.inner*16)
- let cse_var_18: int32 = (elem_idx*16)
- let cse_var_17: int32 = (cse_var_19 + 1)
- let cse_var_16: int32 = (cse_var_19 + 11)
- let cse_var_15: int32 = (cse_var_19 + 12)
- let cse_var_14: int32 = (cse_var_19 + 13)
- let cse_var_13: int32 = (cse_var_19 + 14)
- let cse_var_12: int32 = (cse_var_19 + 15)
- let cse_var_11: int32 = (cse_var_19 + 2)
- let cse_var_10: int32 = (cse_var_19 + 3)
- let cse_var_9: int32 = (cse_var_19 + 4)
- let cse_var_8: int32 = (cse_var_19 + 5)
- let cse_var_7: int32 = (cse_var_19 + 6)
- let cse_var_6: int32 = (cse_var_19 + 7)
- let cse_var_5: int32 = (cse_var_19 + 8)
- let cse_var_4: int32 = (cse_var_19 + 9)
- let cse_var_3: int32 = (cse_var_19 + 10)
- let cse_var_2: int32 = ((i0.outer*16384) + (i.inner*256))
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[i1.outer]*16) + cse_var_18)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 1)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 2)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 3)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 4)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 5)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 6)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 7)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 8)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 9)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 10)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 11)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 12)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 13)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 14)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[i1.outer]*16) + cse_var_18) + 15)]*max(placeholder[(cse_var_2 + placeholder_2[(placeholder_3[i1.outer] + elem_idx)])], 0f32)))
+ for (elem_idx: int32, 0, let cse_var_1: int32 = floormod(i0.outer.i1.outer.fused, 32) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 16) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = floormod(i0.outer.i1.outer.fused, 32)
+ let cse_var_2: int32 = (((i.outer.inner*256) + (i.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[((((floordiv(i0.outer.i1.outer.fused, 32)*8192) + (i.outer.inner*4096)) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
+ }
}
}
}
- for (i0.inner: int32, 0, 64) {
- let cse_var_20: int32 = (((i0.outer*32768) + (i0.inner*512)) + (i1.outer*16))
- compute[ramp(cse_var_20, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_20, 1, 16)]), broadcast(0f32, 16))
+ for (i0.inner: int32, 0, 32) {
+ let cse_var_4: int32 = (((floordiv(i0.outer.i1.outer.fused, 32)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 32)*16))
+ compute[ramp(cse_var_4, 1, 16)] = max((compute_5[ramp((i0.inner*16), 1, 16)] + placeholder_4[ramp(cse_var_4, 1, 16)]), broadcast(0f32, 16))
}
}
}
@@ -706,7 +660,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
</pre></div>
</div>
<p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.827 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.652 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 b3f27e5e6..48269e523 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:45.149</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:44.545</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:44.254</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>00:00.231</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>00:00.222</strong>: <a class="reference internal" href="tune_relay_arm.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-arm-py"><span class="std std-ref">Auto-tuning a Convolutional Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_arm.py</span></code>)</p></li>
-<li><p><strong>00:00.221</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>00:00.220</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>00:43.644</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>00:00.238</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>00:00.222</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>00:00.222</strong>: <a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></li>
+<li><p><strong>00:00.219</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 52da8daa6..42ed113c8 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: 42.37/42.37 result: MeasureResult(costs=(0.005464217842105263,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6299574375152588, timestamp=1652998473.6206386) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
-No: 7 GFLOPS: 0.00/42.37 result: Traceback (most recent call last):
+No: 6 GFLOPS: 110.63/110.63 result: MeasureResult(costs=(0.002092602168831169,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8660893440246582, timestamp=1653006213.9576814) [('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: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
-No: 11 GFLOPS: 0.00/42.37 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/110.63 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: 0.00/42.37 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/110.63 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: 0x00007f85570affa2
+ 12: 0x00007f8dd9a66fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2667,7 +2667,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 144.07/144.07 result: MeasureResult(costs=(0.0016068514099999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4168341159820557, timestamp=1652998500.097603) [('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: 142.66/142.66 result: MeasureResult(costs=(0.00162276938,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4110479354858398, timestamp=1653006240.4081233) [('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: 0.001991
+Time cost of this operator: 0.002064
</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 d34654997..5f40c2737 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -553,10 +553,10 @@ the tuned operator.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.7 98.754 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.07 0.963 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.283 (1, 1, 10, 10, 3) 1 1
-Total_time - 318.671 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 314.1 98.745 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.966 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.919 0.289 (1, 1, 10, 10, 3) 1 1
+Total_time - 318.092 - - - -
</pre></div>
</div>
</div>
@@ -608,10 +608,10 @@ Total_time -
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 80.65 96.794 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.75 2.1 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.921 1.105 (1, 1, 10, 10, 3) 1 1
-Total_time - 83.321 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 151.8 98.251 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.77 1.146 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.931 0.603 (1, 1, 10, 10, 3) 1 1
+Total_time - 154.502 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 0896a0a99..8132ce636 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -300,13 +300,13 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:47.288</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>00:46.347</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:42.924</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>00:03.743</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>00:00.210</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>00:00.209</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>00:00.201</strong>: <a class="reference internal" href="micro_reference_vm.html#sphx-glr-how-to-work-with-microtvm-micro-reference-vm-py"><span class="std std-ref">microTVM Reference Virtual Machines</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_reference_vm.py</span></code>)</p></li>
+<li><p><strong>00:42.115</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>00:03.624</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>00:00.207</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>00:00.202</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>00:00.199</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 ee4c0e103..8d82dd833 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>00:11.314</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.105</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:08.1000</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>00:02.088</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>
+<li><p><strong>00:07.092</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>00:01.790</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>00:00.224</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 27ae98146..61bd4b6e4 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>00:05.946</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:05.694</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<ul class="simple">
-<li><p><strong>00:02.127</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>00:01.321</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>00:00.744</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>00:00.727</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>00:00.314</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>00:00.248</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>00:00.240</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>00:00.226</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>00:02.070</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>00:01.161</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>00:00.727</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>00:00.720</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>00:00.310</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>00:00.245</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>00:00.235</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>00:00.225</strong>: <a class="reference internal" href="tuple_inputs.html#sphx-glr-how-to-work-with-schedules-tuple-inputs-py"><span class="std std-ref">Compute and Reduce with Tuple Inputs</span></a> (<code class="docutils literal notranslate"><span class="pre">tuple_inputs.py</span></code>)</p></li>
</ul>
</div>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index c8539c776..a029ea679 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/tmpsi5tzvuq/input0.cc'\nsource_filename = \"/tmp/tmpsi5tzvuq/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/tmp6xk27wz5/input0.cc'\nsource_filename = \"/tmp/tmp6xk27wz5/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/objects.inv b/docs/objects.inv
index cea49902c..82ab57482 100644
Binary files a/docs/objects.inv and b/docs/objects.inv differ
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 21c3a1bd6..01e1dc6c3 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/python/autotvm.html b/docs/reference/api/python/autotvm.html
index 877751a9d..976e4fa44 100644
--- a/docs/reference/api/python/autotvm.html
+++ b/docs/reference/api/python/autotvm.html
@@ -2164,6 +2164,28 @@ One can construct a new <cite>ConfigEntity</cite> if this is not the case.</p>
</dd></dl>
+<dl class="py class">
+<dt class="sig sig-object py" id="tvm.autotvm.task.dispatcher.ApplyFixedConfig">
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.autotvm.task.dispatcher.</span></span><span class="sig-name descname"><span class="pre">ApplyFixedConfig</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tasks</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">schedule_names</span></span><span class="p"><span class="pre">:</span></span> <span c [...]
+<dd><p>Apply a config of a deterministic schedule.
+This is used for building a single Relay operator with deterministic schedule
+for testing schedules at Relay level.</p>
+<dl class="field-list simple">
+<dt class="field-odd">Parameters</dt>
+<dd class="field-odd"><ul class="simple">
+<li><p><strong>tasks</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.10)"><em>list</em></a><em>[</em><a class="reference internal" href="#tvm.autotvm.task.task.Task" title="tvm.autotvm.task.task.Task"><em>tvm.autotvm.task.task.Task</em></a><em>]</em>) – List of autoTVM tasks.</p></li>
+<li><p><strong>schedule_names</strong> (<a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>, </em><em>List</em><em>[</em><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.10)"><em>str</em></a><em>]</em>) – Name of schedules to use.</p></li>
+</ul>
+</dd>
+</dl>
+<dl class="py method">
+<dt class="sig sig-object py" id="tvm.autotvm.task.dispatcher.ApplyFixedConfig.update">
+<span class="sig-name descname"><span class="pre">update</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">target</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">workload</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">cfg</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.autotvm.task.dispatcher.ApplyFixedConfig.update" title="Permalink to this defin [...]
+<dd><p>Override update</p>
+</dd></dl>
+
+</dd></dl>
+
<dl class="py class">
<dt class="sig sig-object py" id="tvm.autotvm.task.dispatcher.ApplyHistoryBest">
<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.autotvm.task.dispatcher.</span></span><span class="sig-name descname"><span class="pre">ApplyHistoryBest</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">records</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#tvm.autotvm.task.dispatcher.ApplyHistoryBest" title="Permalink to this definitio [...]
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 12568579f..06d8a2e5a 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/cd269101b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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 f7d4e50e3..ce6b2136b 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/cd269101b/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/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/cd269101b/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L363">memory.ts:363</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -574,7 +574,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L346">memory.ts:346</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -600,7 +600,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L334">memory.ts:334</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
diff --git a/docs/reference/api/typedoc/classes/dldatatype.html b/docs/reference/api/typedoc/classes/dldatatype.html
index 6bd7a0c1f..ddeb46ffc 100644
--- a/docs/reference/api/typedoc/classes/dldatatype.html
+++ b/docs/reference/api/typedoc/classes/dldatatype.html
@@ -119,7 +119,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">bits<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L260">runtime.ts:260</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">code<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L258">runtime.ts:258</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -177,7 +177,7 @@
<div class="tsd-signature tsd-kind-icon">lanes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L262">runtime.ts:262</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -199,7 +199,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L279">runtime.ts:279</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -216,7 +216,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L270">runtime.ts:270</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/dldevice.html b/docs/reference/api/typedoc/classes/dldevice.html
index 68836124b..437f31bd3 100644
--- a/docs/reference/api/typedoc/classes/dldevice.html
+++ b/docs/reference/api/typedoc/classes/dldevice.html
@@ -118,7 +118,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L202">runtime.ts:202</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L200">runtime.ts:200</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -161,7 +161,7 @@
<div class="tsd-signature tsd-kind-icon">device<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L198">runtime.ts:198</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -183,7 +183,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L223">runtime.ts:223</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -205,7 +205,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L230">runtime.ts:230</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">string</span></h4>
diff --git a/docs/reference/api/typedoc/classes/environment.html b/docs/reference/api/typedoc/classes/environment.html
index 54b29be5e..d03519a52 100644
--- a/docs/reference/api/typedoc/classes/environment.html
+++ b/docs/reference/api/typedoc/classes/environment.html
@@ -125,7 +125,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L86">environment.ts:86</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -169,7 +169,7 @@
<aside class="tsd-sources">
<p>Implementation of <a href="../interfaces/libraryprovider.html">LibraryProvider</a>.<a href="../interfaces/libraryprovider.html#imports">imports</a></p>
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L70">environment.ts:70</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L69">environment.ts:69</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -210,7 +210,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">ctypes.FTVMWasmPackedCFunc</span><span class="tsd-signature-symbol"> | </span><span class="tsd-signature-type">undefined</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = [undefined,]</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L78">environment.ts:78</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -228,7 +228,7 @@
<div class="tsd-signature tsd-kind-icon">packedCFunc<wbr>Table<wbr>Free<wbr>Id<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span><span class="tsd-signature-symbol"> = []</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L84">environment.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -250,7 +250,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/environment.ts#L105">environment.ts:105</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ffilibrary.html b/docs/reference/api/typedoc/classes/ffilibrary.html
index 583d51069..a28e14ba5 100644
--- a/docs/reference/api/typedoc/classes/ffilibrary.html
+++ b/docs/reference/api/typedoc/classes/ffilibrary.html
@@ -131,7 +131,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L49">runtime.ts:49</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L46">runtime.ts:46</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L45">runtime.ts:45</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L44">runtime.ts:44</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">webGPUContext<span class="tsd-signature-symbol">:</span> <a href="webgpucontext.html" class="tsd-signature-type">WebGPUContext</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L47">runtime.ts:47</a></li>
</ul>
</aside>
</section>
@@ -203,7 +203,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L76">runtime.ts:76</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -226,7 +226,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L66">runtime.ts:66</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -243,7 +243,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L84">runtime.ts:84</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <a href="cachedcallstack.html" class="tsd-signature-type">CachedCallStack</a></h4>
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L95">runtime.ts:95</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -283,7 +283,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L72">runtime.ts:72</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
diff --git a/docs/reference/api/typedoc/classes/graphexecutor.html b/docs/reference/api/typedoc/classes/graphexecutor.html
index 88e634913..432ae8b9e 100644
--- a/docs/reference/api/typedoc/classes/graphexecutor.html
+++ b/docs/reference/api/typedoc/classes/graphexecutor.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L583">runtime.ts:583</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">module<span class="tsd-signature-symbol">:</span> <a href="module.html" class="tsd-signature-type">Module</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L579">runtime.ts:579</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L654">runtime.ts:654</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -224,7 +224,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L597">runtime.ts:597</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -241,7 +241,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L631">runtime.ts:631</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L644">runtime.ts:644</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -310,7 +310,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L621">runtime.ts:621</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -332,7 +332,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L609">runtime.ts:609</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/instance.html b/docs/reference/api/typedoc/classes/instance.html
index 249eeca59..c01f0af5a 100644
--- a/docs/reference/api/typedoc/classes/instance.html
+++ b/docs/reference/api/typedoc/classes/instance.html
@@ -139,7 +139,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L692">runtime.ts:692</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -202,7 +202,7 @@
<div class="tsd-signature tsd-kind-icon">exports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">Function</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L684">runtime.ts:684</a></li>
</ul>
</aside>
</section>
@@ -212,7 +212,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L683">runtime.ts:683</a></li>
</ul>
</aside>
</section>
@@ -229,7 +229,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L932">runtime.ts:932</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -260,7 +260,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L994">runtime.ts:994</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -303,7 +303,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L924">runtime.ts:924</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -341,7 +341,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L732">runtime.ts:732</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -358,7 +358,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L952">runtime.ts:952</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -402,7 +402,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L816">runtime.ts:816</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -434,7 +434,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -465,7 +465,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L846">runtime.ts:846</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -497,7 +497,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L750">runtime.ts:750</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -520,7 +520,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -568,7 +568,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L789">runtime.ts:789</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -608,7 +608,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L914">runtime.ts:914</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -646,7 +646,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -698,7 +698,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L740">runtime.ts:740</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -722,7 +722,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L868">runtime.ts:868</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -754,7 +754,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L857">runtime.ts:857</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -786,7 +786,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L940">runtime.ts:940</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/memory.html b/docs/reference/api/typedoc/classes/memory.html
index 2cac931b1..5a92f6d4d 100644
--- a/docs/reference/api/typedoc/classes/memory.html
+++ b/docs/reference/api/typedoc/classes/memory.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L40">memory.ts:40</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Memory</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L32">memory.ts:32</a></li>
</ul>
</aside>
</section>
@@ -162,7 +162,7 @@
<div class="tsd-signature tsd-kind-icon">wasm32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">boolean</span><span class="tsd-signature-symbol"> = true</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L33">memory.ts:33</a></li>
</ul>
</aside>
</section>
@@ -179,7 +179,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L154">memory.ts:154</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -210,7 +210,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L90">memory.ts:90</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -233,7 +233,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L97">memory.ts:97</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -256,7 +256,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L74">memory.ts:74</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -279,7 +279,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L81">memory.ts:81</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -302,7 +302,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L104">memory.ts:104</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -325,7 +325,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L132">memory.ts:132</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -362,7 +362,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L145">memory.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -393,7 +393,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L60">memory.ts:60</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -416,7 +416,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L67">memory.ts:67</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -439,7 +439,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L53">memory.ts:53</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -462,7 +462,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L114">memory.ts:114</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -485,7 +485,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L124">memory.ts:124</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">number</span></h4>
@@ -502,7 +502,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/memory.ts#L175">memory.ts:175</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/module.html b/docs/reference/api/typedoc/classes/module.html
index 8995529ff..67b1613a4 100644
--- a/docs/reference/api/typedoc/classes/module.html
+++ b/docs/reference/api/typedoc/classes/module.html
@@ -124,7 +124,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L504">runtime.ts:504</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L502">runtime.ts:502</a></li>
</ul>
</aside>
</section>
@@ -187,7 +187,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L516">runtime.ts:516</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -204,7 +204,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L530">runtime.ts:530</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -236,7 +236,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L561">runtime.ts:561</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/ndarray.html b/docs/reference/api/typedoc/classes/ndarray.html
index 1383c825c..467197a52 100644
--- a/docs/reference/api/typedoc/classes/ndarray.html
+++ b/docs/reference/api/typedoc/classes/ndarray.html
@@ -130,7 +130,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L304">runtime.ts:304</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -158,7 +158,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <a href="dldevice.html" class="tsd-signature-type">DLDevice</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L297">runtime.ts:297</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -173,7 +173,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L293">runtime.ts:293</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -188,7 +188,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L289">runtime.ts:289</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -203,7 +203,7 @@
<div class="tsd-signature tsd-kind-icon">ndim<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L291">runtime.ts:291</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -218,7 +218,7 @@
<div class="tsd-signature tsd-kind-icon">shape<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L295">runtime.ts:295</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -240,7 +240,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L370">runtime.ts:370</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -273,7 +273,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L414">runtime.ts:414</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -305,7 +305,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L355">runtime.ts:355</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
@@ -322,7 +322,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L474">runtime.ts:474</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -346,7 +346,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L443">runtime.ts:443</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/packedfunccell.html b/docs/reference/api/typedoc/classes/packedfunccell.html
index f51bc5f67..d6fbe2c8d 100644
--- a/docs/reference/api/typedoc/classes/packedfunccell.html
+++ b/docs/reference/api/typedoc/classes/packedfunccell.html
@@ -122,7 +122,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L158">runtime.ts:158</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -147,7 +147,7 @@
<div class="tsd-signature tsd-kind-icon">handle<span class="tsd-signature-symbol">:</span> <a href="../index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L157">runtime.ts:157</a></li>
</ul>
</aside>
</section>
@@ -164,7 +164,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L165">runtime.ts:165</a></li>
</ul>
</aside>
<h4 class="tsd-returns-title">Returns <span class="tsd-signature-type">void</span></h4>
diff --git a/docs/reference/api/typedoc/classes/rpcserver.html b/docs/reference/api/typedoc/classes/rpcserver.html
index 970a7bc14..b8555ff11 100644
--- a/docs/reference/api/typedoc/classes/rpcserver.html
+++ b/docs/reference/api/typedoc/classes/rpcserver.html
@@ -115,7 +115,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">get<wbr>Imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">unknown</span><span class="tsd-signat [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -201,7 +201,7 @@
<div class="tsd-signature tsd-kind-icon">key<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
</ul>
</aside>
</section>
@@ -211,7 +211,7 @@
<div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>msg<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
</ul>
</aside>
<div class="tsd-type-declaration">
@@ -242,7 +242,7 @@
<div class="tsd-signature tsd-kind-icon">socket<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">WebSocket</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
</ul>
</aside>
</section>
@@ -252,7 +252,7 @@
<div class="tsd-signature tsd-kind-icon">state<span class="tsd-signature-symbol">:</span> <a href="../enums/rpcserverstate.html" class="tsd-signature-type">RPCServerState</a><span class="tsd-signature-symbol"> = RPCServerState.InitHeader</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
</ul>
</aside>
</section>
@@ -262,7 +262,7 @@
<div class="tsd-signature tsd-kind-icon">url<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/classes/scalar.html b/docs/reference/api/typedoc/classes/scalar.html
index f528cd4bb..96947b77a 100644
--- a/docs/reference/api/typedoc/classes/scalar.html
+++ b/docs/reference/api/typedoc/classes/scalar.html
@@ -112,7 +112,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -137,7 +137,7 @@
<div class="tsd-signature tsd-kind-icon">dtype<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L145">runtime.ts:145</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -152,7 +152,7 @@
<div class="tsd-signature tsd-kind-icon">value<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L143">runtime.ts:143</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/classes/webgpucontext.html b/docs/reference/api/typedoc/classes/webgpucontext.html
index d035ecee2..f9f12e44c 100644
--- a/docs/reference/api/typedoc/classes/webgpucontext.html
+++ b/docs/reference/api/typedoc/classes/webgpucontext.html
@@ -120,7 +120,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
</ul>
</aside>
<h4 class="tsd-parameters-title">Parameters</h4>
@@ -145,7 +145,7 @@
<div class="tsd-signature tsd-kind-icon">device<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">GPUDevice</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
</ul>
</aside>
</section>
@@ -155,7 +155,7 @@
<div class="tsd-signature tsd-kind-icon">memory<span class="tsd-signature-symbol">:</span> <a href="memory.html" class="tsd-signature-type">Memory</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
</ul>
</aside>
</section>
@@ -172,7 +172,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -209,7 +209,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/enums/argtypecode.html b/docs/reference/api/typedoc/enums/argtypecode.html
index 79496675f..145a2ab64 100644
--- a/docs/reference/api/typedoc/enums/argtypecode.html
+++ b/docs/reference/api/typedoc/enums/argtypecode.html
@@ -106,7 +106,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 6</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
</ul>
</aside>
</section>
@@ -116,7 +116,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
</ul>
</aside>
</section>
@@ -126,7 +126,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
</ul>
</aside>
</section>
@@ -136,7 +136,7 @@
<div class="tsd-signature tsd-kind-icon">Null<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
</ul>
</aside>
</section>
@@ -146,7 +146,7 @@
<div class="tsd-signature tsd-kind-icon">TVMBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 12</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
</ul>
</aside>
</section>
@@ -156,7 +156,7 @@
<div class="tsd-signature tsd-kind-icon">TVMDLTensor<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
</ul>
</aside>
</section>
@@ -166,7 +166,7 @@
<div class="tsd-signature tsd-kind-icon">TVMData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
</ul>
</aside>
</section>
@@ -176,7 +176,7 @@
<div class="tsd-signature tsd-kind-icon">TVMModule<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 9</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
</ul>
</aside>
</section>
@@ -186,7 +186,7 @@
<div class="tsd-signature tsd-kind-icon">TVMNDArray<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 13</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
</ul>
</aside>
</section>
@@ -196,7 +196,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObject<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
</ul>
</aside>
</section>
@@ -206,7 +206,7 @@
<div class="tsd-signature tsd-kind-icon">TVMObjectRValue<wbr>Ref<wbr>Arg<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 14</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
</ul>
</aside>
</section>
@@ -216,7 +216,7 @@
<div class="tsd-signature tsd-kind-icon">TVMOpaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
</ul>
</aside>
</section>
@@ -226,7 +226,7 @@
<div class="tsd-signature tsd-kind-icon">TVMPacked<wbr>Func<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 10</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
</ul>
</aside>
</section>
@@ -236,7 +236,7 @@
<div class="tsd-signature tsd-kind-icon">TVMStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 11</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
</ul>
</aside>
</section>
@@ -246,7 +246,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/aynccallbackcode.html b/docs/reference/api/typedoc/enums/aynccallbackcode.html
index 5f8b64dc3..cf8787068 100644
--- a/docs/reference/api/typedoc/enums/aynccallbackcode.html
+++ b/docs/reference/api/typedoc/enums/aynccallbackcode.html
@@ -93,7 +93,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Exception<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 5</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L676">runtime.ts:676</a></li>
</ul>
</aside>
</section>
@@ -103,7 +103,7 @@
<div class="tsd-signature tsd-kind-icon">k<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L675">runtime.ts:675</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/dldatatypecode.html b/docs/reference/api/typedoc/enums/dldatatypecode.html
index 67e9e95c6..bbbea681d 100644
--- a/docs/reference/api/typedoc/enums/dldatatypecode.html
+++ b/docs/reference/api/typedoc/enums/dldatatypecode.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">Float<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L242">runtime.ts:242</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">Int<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 0</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L240">runtime.ts:240</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">Opaque<wbr>Handle<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 3</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L243">runtime.ts:243</a></li>
</ul>
</aside>
</section>
@@ -125,7 +125,7 @@
<div class="tsd-signature tsd-kind-icon">UInt<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/runtime.ts#L241">runtime.ts:241</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/rpcserverstate.html b/docs/reference/api/typedoc/enums/rpcserverstate.html
index 65d34547b..c306b7a7a 100644
--- a/docs/reference/api/typedoc/enums/rpcserverstate.html
+++ b/docs/reference/api/typedoc/enums/rpcserverstate.html
@@ -90,7 +90,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
</ul>
</aside>
</section>
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Header<wbr>Key<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">Init<wbr>Server<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Body<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">Receive<wbr>Packet<wbr>Header<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">Wait<wbr>For<wbr>Callback<span class="tsd-signature-symbol">:</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/enums/sizeof.html b/docs/reference/api/typedoc/enums/sizeof.html
index 6502dfd1a..aeefa7fe8 100644
--- a/docs/reference/api/typedoc/enums/sizeof.html
+++ b/docs/reference/api/typedoc/enums/sizeof.html
@@ -100,7 +100,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
</ul>
</aside>
</section>
@@ -110,7 +110,7 @@
<div class="tsd-signature tsd-kind-icon">DLDevice<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = I32 + I32</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
</ul>
</aside>
</section>
@@ -120,7 +120,7 @@
<div class="tsd-signature tsd-kind-icon">F32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/5e29dddd0/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
</ul>
</aside>
</section>
@@ -130,7 +130,7 @@
<div class="tsd-signature tsd-kind-icon">F64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/cd269101b/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
... 1302 lines suppressed ...