You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by tq...@apache.org on 2022/06/24 18:58:40 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@f1d30a27b2efe5b15e6492f785be1d41c9a75ab9)
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 ada42e9c2 deploying docs (apache/tvm@f1d30a27b2efe5b15e6492f785be1d41c9a75ab9)
ada42e9c2 is described below
commit ada42e9c2a361171560be15c465bd34fa0c39344
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Fri Jun 24 18:58:35 2022 +0000
deploying docs (apache/tvm@f1d30a27b2efe5b15e6492f785be1d41c9a75ab9)
---
.../how_to/compile_models/from_mxnet.rst.txt | 2 +-
.../how_to/compile_models/from_oneflow.rst.txt | 2 +-
.../how_to/compile_models/from_paddle.rst.txt | 2 +-
.../how_to/compile_models/from_pytorch.rst.txt | 2 +-
.../how_to/compile_models/from_tensorflow.rst.txt | 2 +-
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 16 +-
.../extend_tvm/bring_your_own_datatypes.rst.txt | 2 +-
.../how_to/extend_tvm/sg_execution_times.rst.txt | 8 +-
.../how_to/extend_tvm/use_pass_instrument.rst.txt | 16 +-
.../optimize_operators/opt_conv_cuda.rst.txt | 2 +-
.../optimize_operators/opt_conv_tensorcore.rst.txt | 2 +-
.../how_to/optimize_operators/opt_gemm.rst.txt | 16 +-
.../optimize_operators/sg_execution_times.rst.txt | 8 +-
.../sg_execution_times.rst.txt | 14 +-
.../tune_conv2d_layer_cuda.rst.txt | 1894 ++++++++++++++++++--
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 81 +-
.../tune_with_autotvm/sg_execution_times.rst.txt | 6 +-
.../tune_with_autotvm/tune_conv2d_cuda.rst.txt | 34 +-
.../work_with_microtvm/micro_autotune.rst.txt | 16 +-
.../how_to/work_with_microtvm/micro_train.rst.txt | 16 +-
.../work_with_microtvm/sg_execution_times.rst.txt | 8 +-
.../work_with_relay/sg_execution_times.rst.txt | 6 +-
.../how_to/work_with_schedules/intrin_math.rst.txt | 2 +-
.../work_with_schedules/sg_execution_times.rst.txt | 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 | 4 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 58 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 22 +-
.../tutorial/tensor_expr_get_started.rst.txt | 47 +-
docs/commit_hash | 2 +-
docs/how_to/compile_models/from_mxnet.html | 2 +-
docs/how_to/compile_models/from_oneflow.html | 125 +-
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 | 22 +-
docs/how_to/deploy_models/deploy_prequantized.html | 13 +-
.../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 | 34 +-
docs/how_to/deploy_models/sg_execution_times.html | 16 +-
.../extend_tvm/bring_your_own_datatypes.html | 2 +-
docs/how_to/extend_tvm/sg_execution_times.html | 8 +-
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 | 1894 ++++++++++++++++++--
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 81 +-
.../tune_with_autotvm/sg_execution_times.html | 6 +-
.../how_to/tune_with_autotvm/tune_conv2d_cuda.html | 34 +-
docs/how_to/work_with_microtvm/micro_autotune.html | 16 +-
docs/how_to/work_with_microtvm/micro_train.html | 16 +-
.../work_with_microtvm/sg_execution_times.html | 8 +-
.../how_to/work_with_relay/sg_execution_times.html | 6 +-
docs/how_to/work_with_schedules/intrin_math.html | 2 +-
.../work_with_schedules/sg_execution_times.html | 18 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 6 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 4 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 4 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 262 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 30 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
121 files changed, 4351 insertions(+), 1324 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 a1b0c0c4f..a101dd87b 100644
--- a/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_mxnet.rst.txt
@@ -114,7 +114,7 @@ In this section, we download a pretrained imagenet model and classify an image.
.. code-block:: none
- Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip486fd0a7-e584-4908-96b1-cf7c8949d1b2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7711d7c2-bb2d-4ab9-b495-a12f8fe83ee8 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 8d2c088ed..f51d5966e 100644
--- a/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_oneflow.rst.txt
@@ -112,7 +112,7 @@ Load a pretrained OneFlow model and save model
.. code-block:: none
Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
-
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<09:48, 73.9kB/s]
0%| | 40.0k/41.5M [00:00<07:31, 96.2kB/s]
0%| | 96.0k/41.5M [00:00<03:59, 181kB/s]
0%| | 160k/41.5M [00:00<02:55, 248kB/s]
1%| | 328k/41.5M [00:01<01:31, 474kB/s]
1%|1 | 536k/41.5M [00:01<01:05, 652kB/s]
2%|1 | 744k/41.5M [00:01<00:56, 756kB/s]
2%|2 | 952k/41.5M [00:01<00:51, 829kB/s]
3%|2 | 1.13M/41.5M [00:01<00:47, 899kB/s]
3%|3 | 1.34M/41.5M [00:02<00:44, 946kB/s]
4%|3 | 1.54M/41.5M [00:02<00:44, 949kB/s]
4%|4 | 1.74M/41.5M [00:02<00:43, 952kB/s]
5%|4 | 1.95M/41.5M [00:02<00:42, 966kB/s]
5%|5 | 2.16M/41.5M [00:02<00:40, 1.01MB/s]
6%|5 | 2.37M/41.5M [00:03<00:38, 1.06MB/s]
6%|6 | 2.58M/41.5M [00:03<00:39, 1.03MB/s]
7%|6 | 2.79M/41.5M [00:03<00:39, 1.0
2MB/s]
7%|7 | 3.00M/41.5M [00:03<00:39, 1.01MB/s]
8%|7 | 3.21M/41.5M [00:03<00:38, 1.05MB/s]
8%|8 | 3.43M/41.5M [00:04<00:36, 1.09MB/s]
9%|8 | 3.66M/41.5M [00:04<00:36, 1.08MB/s]
9%|9 | 3.88M/41.5M [00:04<00:37, 1.07MB/s]
10%|9 | 4.11M/41.5M [00:04<00:35, 1.09MB/s]
10%|# | 4.34M/41.5M [00:05<00:34, 1.14MB/s]
11%|#1 | 4.58M/41.5M [00:05<00:33, 1.16MB/s]
12%|#1 | 4.81M/41.5M [00:05<00:27, 1.38MB/s]
12%|#1 | 4.96M/41.5M [00:05<00:28, 1.35MB/s]
12%|#2 | 5.10M/41.5M [00:05<00:34, 1.09MB/s]
13%|#2 | 5.33M/41.5M [00:05<00:34, 1.10MB/s]
13%|#3 | 5.59M/41.5M [00:06<00:31, 1.20MB/s]
14%|#4 | 5.87M/41.5M [00:06<00:29, 1.27MB/s]
15%|#4 | 6.13M/41.5M [00:06<00:24, 1.51MB/s]
15%|#5 | 6.30M/41.5M [00:06<00:25, 1.45MB/s]
16%|#5 | 6.45M/41.5M [00:06<00:31, 1.17MB/s]
16%|#6 |
6.74M/41.5M [00:06<00:27, 1.33MB/s]
17%|#7 | 7.06M/41.5M [00:07<00:24, 1.45MB/s]
18%|#7 | 7.38M/41.5M [00:07<00:19, 1.80MB/s]
18%|#8 | 7.58M/41.5M [00:07<00:20, 1.70MB/s]
19%|#8 | 7.76M/41.5M [00:07<00:25, 1.38MB/s]
20%|#9 | 8.10M/41.5M [00:07<00:22, 1.53MB/s]
20%|## | 8.47M/41.5M [00:07<00:17, 1.95MB/s]
21%|## | 8.69M/41.5M [00:08<00:18, 1.89MB/s]
21%|##1 | 8.89M/41.5M [00:08<00:21, 1.59MB/s]
22%|##2 | 9.28M/41.5M [00:08<00:19, 1.76MB/s]
23%|##3 | 9.70M/41.5M [00:08<00:15, 2.22MB/s]
24%|##3 | 9.94M/41.5M [00:08<00:15, 2.10MB/s]
24%|##4 | 10.2M/41.5M [00:08<00:18, 1.76MB/s]
26%|##5 | 10.6M/41.5M [00:09<00:16, 2.00MB/s]
27%|##6 | 11.1M/41.5M [00:09<00:14, 2.21MB/s]
28%|##7 | 11.6M/41.5M [00:09<00:13, 2.25MB/s]
29%|##9 | 12.1M/41.5M [00:09<00:13, 2.35MB/s]
31%|### | 12.7M/41.5M [00:09<00:10, 2.
94MB/s]
31%|###1 | 13.0M/41.5M [00:09<00:10, 2.84MB/s]
32%|###2 | 13.3M/41.5M [00:10<00:12, 2.41MB/s]
33%|###3 | 13.9M/41.5M [00:10<00:10, 2.82MB/s]
35%|###4 | 14.5M/41.5M [00:10<00:07, 3.57MB/s]
36%|###5 | 14.9M/41.5M [00:10<00:09, 3.08MB/s]
37%|###6 | 15.2M/41.5M [00:10<00:10, 2.59MB/s]
38%|###8 | 15.9M/41.5M [00:10<00:07, 3.47MB/s]
39%|###9 | 16.3M/41.5M [00:11<00:07, 3.42MB/s]
40%|#### | 16.7M/41.5M [00:11<00:08, 3.10MB/s]
42%|####2 | 17.4M/41.5M [00:11<00:06, 4.05MB/s]
44%|####3 | 18.2M/41.5M [00:11<00:04, 4.94MB/s]
45%|####5 | 18.7M/41.5M [00:11<00:05, 4.18MB/s]
46%|####6 | 19.2M/41.5M [00:11<00:06, 3.40MB/s]
48%|####8 | 20.0M/41.5M [00:11<00:05, 4.13MB/s]
50%|##### | 20.9M/41.5M [00:12<00:04, 5.04MB/s]
52%|#####1 | 21.4M/41.5M [00:12<00:04, 4.35MB/s]
53%|#####2 | 21.9M/41.5M [00:12<00:04, 4.44MB/s]
55%|#####5 |
22.9M/41.5M [00:12<00:03, 5.67MB/s]
57%|#####6 | 23.5M/41.5M [00:12<00:04, 4.65MB/s]
58%|#####7 | 24.0M/41.5M [00:12<00:04, 4.55MB/s]
60%|###### | 25.1M/41.5M [00:12<00:02, 5.87MB/s]
62%|######1 | 25.7M/41.5M [00:13<00:03, 4.84MB/s]
63%|######3 | 26.3M/41.5M [00:13<00:03, 5.07MB/s]
66%|######6 | 27.5M/41.5M [00:13<00:02, 6.64MB/s]
68%|######7 | 28.2M/41.5M [00:13<00:02, 5.93MB/s]
69%|######9 | 28.8M/41.5M [00:13<00:02, 5.74MB/s]
72%|#######1 | 29.8M/41.5M [00:13<00:01, 6.84MB/s]
74%|#######3 | 30.5M/41.5M [00:13<00:02, 5.38MB/s]
76%|#######5 | 31.5M/41.5M [00:14<00:01, 5.94MB/s]
79%|#######9 | 32.9M/41.5M [00:14<00:01, 7.82MB/s]
81%|########1 | 33.8M/41.5M [00:14<00:01, 6.90MB/s]
83%|########3 | 34.5M/41.5M [00:14<00:01, 6.01MB/s]
87%|########6 | 35.9M/41.5M [00:14<00:00, 7.10MB/s]
90%|########9 | 37.3M/41.5M [00:14<00:00, 8.58MB/s]
92%|#########2| 38.2M/41.5M [00:14<00:00, 7
.13MB/s]
94%|#########3| 39.0M/41.5M [00:15<00:00, 5.97MB/s]
97%|#########7| 40.3M/41.5M [00:15<00:00, 7.34MB/s]
100%|##########| 41.5M/41.5M [00:15<00:00, 2.82MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:42, 94.0kB/s]
0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
0%| | 96.0k/41.5M [00:00<03:27, 209kB/s]
0%| | 208k/41.5M [00:00<01:52, 385kB/s]
1%|1 | 432k/41.5M [00:00<00:59, 718kB/s]
2%|2 | 872k/41.5M [00:01<00:31, 1.35MB/s]
4%|4 | 1.72M/41.5M [00:01<00:16, 2.60MB/s]
8%|7 | 3.26M/41.5M [00:01<00:08, 4.70MB/s]
12%|#1 | 4.80M/41.5M [00:01<00:06, 6.11MB/s]
15%|#5 | 6.34M/41.5M [00:01<00:05, 7.07MB/s]
19%|#8 | 7.88M/41.5M [00:01<00:04, 7.72MB/s]
23%|##2 | 9.41M/41.5M [00:02<00:04, 8.17MB/s]
26%|##6 | 10.9M/41.5M [00:02<00:03, 8.47MB/s]
30%|### | 12.5M/41.5M [00:02<00:03, 8.69MB/s]
34%|###3 | 14.0M/41.5M [00:02<00:03, 8.82MB/s]
37%|###7 | 15.5M/41.5M [00:02<00:03, 8.93MB/s]
41%|####1 | 17.1M/41.5M [00:02<0
0:02, 9.02MB/s]
45%|####4 | 18.6M/41.5M [00:03<00:02, 9.06MB/s]
49%|####8 | 20.2M/41.5M [00:03<00:02, 9.10MB/s]
52%|#####2 | 21.7M/41.5M [00:03<00:02, 9.09MB/s]
56%|#####5 | 23.2M/41.5M [00:03<00:02, 9.12MB/s]
60%|#####9 | 24.8M/41.5M [00:03<00:01, 9.15MB/s]
63%|######3 | 26.3M/41.5M [00:04<00:01, 9.16MB/s]
66%|######5 | 27.2M/41.5M [00:04<00:01, 7.56MB/s]
69%|######9 | 28.8M/41.5M [00:04<00:01, 8.03MB/s]
71%|#######1 | 29.6M/41.5M [00:04<00:01, 7.69MB/s]
75%|#######5 | 31.2M/41.5M [00:04<00:01, 8.16MB/s]
79%|#######8 | 32.7M/41.5M [00:04<00:01, 8.47MB/s]
83%|########2 | 34.2M/41.5M [00:05<00:00, 8.70MB/s]
86%|########6 | 35.8M/41.5M [00:05<00:00, 8.84MB/s]
90%|########9 | 37.3M/41.5M [00:05<00:00, 8.95MB/s]
94%|#########3| 38.9M/41.5M [00:05<00:00, 9.00MB/s]
97%|#########7| 40.4M/41.5M [00:05<00:00, 9.06MB/s]
99%|#########9| 41.3M/41.5M [00:06<00:00, 7.35MB/s]
100%|###
#######| 41.5M/41.5M [00:06<00:00, 7.24MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_paddle.rst.txt b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
index 0594bc0ed..fa9a431c9 100644
--- a/docs/_sources/how_to/compile_models/from_paddle.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_paddle.rst.txt
@@ -235,7 +235,7 @@ Look up prediction top 1 index in 1000 class synset.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 9.376 seconds)
+ **Total running time of the script:** ( 1 minutes 5.825 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 4a47cdce0..822c8dd5a 100644
--- a/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_pytorch.rst.txt
@@ -93,7 +93,7 @@ Load a pretrained PyTorch model
.. code-block:: none
Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
-
0%| | 0.00/44.7M [00:00<?, ?B/s]
46%|####5 | 20.4M/44.7M [00:00<00:00, 214MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 244MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
9%|8 | 3.95M/44.7M [00:00<00:01, 41.4MB/s]
27%|##7 | 12.2M/44.7M [00:00<00:00, 68.1MB/s]
62%|######2 | 27.8M/44.7M [00:00<00:00, 111MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 122MB/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 ae123ebe5..be5f4b5f8 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -422,7 +422,7 @@ Run the corresponding model on tensorflow
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 4.892 seconds)
+ **Total running time of the script:** ( 1 minutes 1.946 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 6973d3a93..ae7904548 100644
--- a/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/compile_models/sg_execution_times.rst.txt
@@ -5,26 +5,26 @@
Computation times
=================
-**05:44.307** total execution time for **how_to_compile_models** files:
+**05:22.379** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:09.376 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:05.825 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:04.892 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:01.946 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:59.982 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:57.694 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:44.635 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:31.859 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:24.085 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.901 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.972 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:23.763 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:22.015 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.567 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.534 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:19.344 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.256 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.126 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.355 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
index 11911c3d6..20c703230 100644
--- a/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_model_on_android.rst.txt
@@ -440,7 +440,7 @@ Execute on TVM
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3085 16.2316 16.6068 16.1153 0.1688
+ 15.9979 15.9347 16.5312 15.7462 0.2189
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 b4ccda273..765e0cd0a 100644
--- a/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_object_detection_pytorch.rst.txt
@@ -122,7 +122,7 @@ Load pre-trained maskrcnn from torchvision and do tracing
.. code-block:: none
Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
-
0%| | 0.00/170M [00:00<?, ?B/s]
3%|2 | 4.85M/170M [00:00<00:03, 50.8MB/s]
6%|5 | 9.91M/170M [00:00<00:03, 52.1MB/s]
20%|## | 34.1M/170M [00:00<00:00, 144MB/s]
35%|###4 | 59.3M/170M [00:00<00:00, 192MB/s]
50%|####9 | 84.3M/170M [00:00<00:00, 217MB/s]
64%|######4 | 109M/170M [00:00<00:00, 232MB/s]
79%|#######8 | 134M/170M [00:00<00:00, 241MB/s]
94%|#########3| 159M/170M [00:00<00:00, 248MB/s]
100%|##########| 170M/170M [00:00<00:00, 211MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
1%| | 1.27M/170M [00:00<00:13, 13.1MB/s]
2%|2 | 3.42M/170M [00:00<00:09, 18.4MB/s]
5%|4 | 8.40M/170M [00:00<00:05, 33.6MB/s]
11%|#1 | 19.1M/170M [00:00<00:02, 64.2MB/s]
24%|##3 | 40.3M/170M [00:00<00:01, 121MB/s]
37%|###7 | 63.6M/170M [00:00<00:00, 163MB/s]
51%|#####1 | 87.3M/170M [00:00<00:00, 191MB/s]
65%|######5 | 111M/170M [00:00<00:00, 208MB/s]
79%|#######9 | 135M/170M [00:00<00:00, 221MB/s]
93%|#########3| 158M/170M [00:01<00:00, 229MB/s]
100%|##########| 170M/170M [00:01<00:00, 169MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 59.141 seconds)
+ **Total running time of the script:** ( 2 minutes 54.429 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 585c82b57..176e69ae0 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized.rst.txt
@@ -219,7 +219,7 @@ training. Other models require a full post training calibration.
.. code-block:: none
Downloading: "https://download.pytorch.org/models/mobilenet_v2-b0353104.pth" to /workspace/.cache/torch/hub/checkpoints/mobilenet_v2-b0353104.pth
-
0%| | 0.00/13.6M [00:00<?, ?B/s]
20%|#9 | 2.68M/13.6M [00:00<00:00, 27.6MB/s]
60%|###### | 8.17M/13.6M [00:00<00:00, 45.1MB/s]
92%|#########2| 12.5M/13.6M [00:00<00:00, 34.1MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 34.3MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
6%|6 | 880k/13.6M [00:00<00:01, 8.96MB/s]
18%|#8 | 2.48M/13.6M [00:00<00:00, 13.6MB/s]
40%|#### | 5.43M/13.6M [00:00<00:00, 21.5MB/s]
80%|#######9 | 10.8M/13.6M [00:00<00:00, 35.2MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 32.6MB/s]
@@ -399,7 +399,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3879 90.3525 90.8283 90.2179 0.1102
+ 90.4646 90.2163 100.8701 90.0853 1.3153
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 8.636 seconds)
+ **Total running time of the script:** ( 1 minutes 7.399 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 050c327cf..d9b28503e 100644
--- a/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_prequantized_tflite.rst.txt
@@ -426,7 +426,7 @@ Here we give an example of how to measure performance of TVM compiled models.
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.2575 120.1504 122.0605 119.3781 0.4370
+ 119.3751 119.3254 120.2596 118.6613 0.3022
@@ -463,7 +463,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 53.074 seconds)
+ **Total running time of the script:** ( 1 minutes 51.697 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 68eb7dc79..353a22c7c 100644
--- a/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_quantized.rst.txt
@@ -254,7 +254,7 @@ We create a Relay VM to build and execute the model.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 13.619 seconds)
+ **Total running time of the script:** ( 1 minutes 29.035 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 8f3dc8a37..4e7a9c8b9 100644
--- a/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
+++ b/docs/_sources/how_to/deploy_models/deploy_ssd_gluoncv.rst.txt
@@ -157,7 +157,7 @@ Convert and compile model for CPU.
data: None
input_sym_arg_type = in_param.infer_type()[0]
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
-
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6432/132723 [00:00<00:01, 64313.77KB/s]
11%|#1 | 14834/132723 [00:00<00:01, 75900.25KB/s]
18%|#7 | 23314/132723 [00:00<00:01, 79958.82KB/s]
24%|##3 | 31741/132723 [00:00<00:01, 81656.04KB/s]
30%|### | 40158/132723 [00:00<00:01, 82558.86KB/s]
37%|###6 | 48494/132723 [00:00<00:01, 82828.36KB/s]
43%|####2 | 56902/132723 [00:00<00:00, 83235.86KB/s]
49%|####9 | 65345/132723 [00:00<00:00, 83612.84KB/s]
56%|#####5 | 73794/132723 [00:00<00:00, 83885.12KB/s]
62%|######1 | 82264/132723 [00:01<00:00, 84135.28KB/s]
68%|######8 | 90687/132723 [00:01<00:00, 84156.61KB/s]
75%|#######4 | 99128/132723 [00:01<00:00, 84231.03KB/s]
81%|########1 | 107593/132723 [00:01<00:00, 84354.43KB/s]
87%|########7 | 116058/132723 [00:01<00:00, 84441.04KB/s]
94%|#########3| 124571/132723 [00:01<00:00, 84638.51KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 83127.04KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
5%|4 | 6010/132723 [00:00<00:02, 60095.90KB/s]
11%|# | 14441/132723 [00:00<00:01, 74337.36KB/s]
17%|#7 | 22880/132723 [00:00<00:01, 78925.54KB/s]
24%|##3 | 31323/132723 [00:00<00:01, 81095.09KB/s]
30%|### | 39842/132723 [00:00<00:01, 82569.00KB/s]
36%|###6 | 48277/132723 [00:00<00:01, 83171.91KB/s]
43%|####2 | 56678/132723 [00:00<00:00, 83443.31KB/s]
49%|####9 | 65163/132723 [00:00<00:00, 83888.20KB/s]
55%|#####5 | 73608/132723 [00:00<00:00, 84060.02KB/s]
62%|######1 | 82087/132723 [00:01<00:00, 84283.34KB/s]
68%|######8 | 90554/132723 [00:01<00:00, 84400.22KB/s]
75%|#######4 | 99024/132723 [00:01<00:00, 84484.57KB/s]
81%|######## | 107473/132723 [00:01<00:00, 84326.68KB/s]
87%|########7 | 115906/132723 [00:01<00:00, 84308.19KB/s]
94%|#########3| 124337/132723 [00:01<00:00, 84249.67KB/s]
100%|########
##| 132723/132723 [00:01<00:00, 82855.34KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 21.941 seconds)
+ **Total running time of the script:** ( 2 minutes 18.036 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 039146dcd..d82d36428 100644
--- a/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/deploy_models/sg_execution_times.rst.txt
@@ -5,22 +5,22 @@
Computation times
=================
-**10:28.651** total execution time for **how_to_deploy_models** files:
+**10:31.098** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:59.141 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:54.429 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:21.941 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:18.036 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:53.074 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:51.697 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:13.619 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:29.035 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:08.636 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.399 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:29.819 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.619 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:22.415 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.878 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_deploy_models_deploy_sparse.py` (``deploy_sparse.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
index 4585e5ad8..9183d07e4 100644
--- a/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/bring_your_own_datatypes.rst.txt
@@ -463,7 +463,7 @@ First let us define two helper functions to get the mobilenet model and a cat im
.. code-block:: none
- Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf6306733-7f7c-47e4-8ebe-430ad30112c3 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip4b5eceb2-88b7-4508-ac97-14ab3565b274 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 1575d89f7..bc119cda8 100644
--- a/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/sg_execution_times.rst.txt
@@ -5,14 +5,14 @@
Computation times
=================
-**00:40.382** total execution time for **how_to_extend_tvm** files:
+**00:39.774** total execution time for **how_to_extend_tvm** files:
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.207 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:36.589 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.257 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.926 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.922 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_extend_tvm_low_level_custom_pass.py` (``low_level_custom_pass.py``) | 00:00.006 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
index b9b2adcd8..04bcb918d 100644
--- a/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
+++ b/docs/_sources/how_to/extend_tvm/use_pass_instrument.rst.txt
@@ -215,10 +215,10 @@ profile the execution time of each passes.
.. code-block:: none
Printing results of timing profile...
- InferType: 6528us [6528us] (45.88%; 45.88%)
- FoldScaleAxis: 7699us [6us] (54.12%; 54.12%)
- FoldConstant: 7693us [1564us] (54.08%; 99.93%)
- InferType: 6129us [6129us] (43.08%; 79.67%)
+ InferType: 7271us [7271us] (46.43%; 46.43%)
+ FoldScaleAxis: 8388us [6us] (53.57%; 53.57%)
+ FoldConstant: 8382us [1669us] (53.53%; 99.93%)
+ InferType: 6713us [6713us] (42.87%; 80.09%)
@@ -257,10 +257,10 @@ Refer to following sections and :py:func:`tvm.instrument.pass_instrument` for th
.. code-block:: none
Printing results of timing profile...
- InferType: 6179us [6179us] (44.70%; 44.70%)
- FoldScaleAxis: 7646us [6us] (55.30%; 55.30%)
- FoldConstant: 7640us [1575us] (55.26%; 99.93%)
- InferType: 6065us [6065us] (43.87%; 79.38%)
+ InferType: 6723us [6723us] (44.81%; 44.81%)
+ FoldScaleAxis: 8281us [5us] (55.19%; 55.19%)
+ FoldConstant: 8276us [1702us] (55.16%; 99.94%)
+ InferType: 6574us [6574us] (43.81%; 79.43%)
diff --git a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
index 11f3d05ac..dab80470b 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_cuda.rst.txt
@@ -327,7 +327,7 @@ latency of convolution.
.. code-block:: none
- Convolution: 54.199867 ms
+ Convolution: 54.142719 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 4f53ee35d..7672c106a 100644
--- a/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_conv_tensorcore.rst.txt
@@ -658,7 +658,7 @@ be able to run on our build server
.. code-block:: none
- conv2d with tensor core: 6.875362 ms
+ conv2d with tensor core: 6.906179 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 8389c0e22..2c61b5545 100644
--- a/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/opt_gemm.rst.txt
@@ -130,8 +130,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
.. code-block:: none
- Numpy running time: 0.019028
- Baseline: 3.404544
+ Numpy running time: 0.019387
+ Baseline: 3.341706
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.323016
+ Opt1: 0.307661
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.352187
+ Opt2: 0.349376
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.119966
+ Opt3: 0.118716
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.110545
+ Opt4: 0.110635
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111549
+ Opt5: 0.111683
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.146698
+ Opt6: 0.145276
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 2b1cfd97f..d437fbbb2 100644
--- a/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/optimize_operators/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:35.118** total execution time for **how_to_optimize_operators** files:
+**00:34.598** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.802 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.358 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.255 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.233 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.060 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.007 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
index b15792519..a605a295f 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/sg_execution_times.rst.txt
@@ -5,18 +5,18 @@
Computation times
=================
-**05:14.820** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:22.741** total execution time for **how_to_tune_with_autoscheduler** files:
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:35.281 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:36.299 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:21.177 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.969 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:43.360 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.898 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.508 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:26.436 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.883 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.588 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.611 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.551 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
index af0b2b9a9..c18382f52 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.rst.txt
@@ -239,107 +239,939 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [672]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
for (rc.outer.outer: int32, 0, 16) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_3: int32 = (rc.outer.outer*1568)
+ let cse_var_2: int32 = (ry.outer.outer*7)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 196), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 588), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 980), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1372), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [672], [], scope="shared")[(threadIdx.x_1*8)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*8), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*8), 21), 3) + ry.outer.outer) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 1), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 2), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 2), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((threa [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 4), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 4), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 4), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 5), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 5), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 5), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 6)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((threa [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 7)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 7), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 7), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 7), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7 [...]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 4), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 20), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 28), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 44), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 588), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 637), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 52), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 686), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 132), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 735), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 20), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 256)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 256), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 256), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 256), 3)*7)) + cse_var_2) + floormod(block [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 257)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 257), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 257), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 257), 3)*7)) + cse_var_2) + floormod(block [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 258)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((thr [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 259)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 1), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 256), 3)*7)) + cse_var_2) + floo [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 260)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 260), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 260), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 260), 3)*7)) + cse_var_2) + floormod(block [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 261)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((thr [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 262)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 2), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 256), 3)*7)) + cse_var_2) + floo [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 263)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 263), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 263), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 263), 3)*7)) + cse_var_2) + floormod(block [...]
}
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 16) {
- let cse_var_8: int32 = (ff.outer.inner*4)
- let cse_var_7: int32 = (cse_var_8 + 3)
- let cse_var_6: int32 = (cse_var_8 + 2)
- let cse_var_5: int32 = (cse_var_8 + 1)
- {
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 96)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 192)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 288)]))
- }
- }
- }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 512)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 512), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 512), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 512), 3)*7)) + cse_var_2) + floormod(blo [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 513)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((t [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 514)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 514), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 514), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 514), 3)*7)) + cse_var_2) + floormod(blo [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 515)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 1), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 512), 3)*7)) + cse_var_2) + fl [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 516)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 4), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((t [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 517)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 517), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 517), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 517), 3)*7)) + cse_var_2) + floormod(blo [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 518)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 2), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 512), 3)*7)) + cse_var_2) + fl [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 519)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 5), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(blockIdx.x, 7)) + floormod((t [...]
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[216]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[217]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[218]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[240]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[243]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[241]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[244]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[242]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[245]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[267]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[270]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[268]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[271]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[269]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[272]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[294]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[297]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[295]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[298]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[296]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[299]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[321]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[324]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[322]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[325]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[323]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[326]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[348]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[351]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[349]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[352]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[350]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[353]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[375]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[376]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[377]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[378]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[379]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[380]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[402]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[405]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[403]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[406]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[404]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[407]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[429]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[432]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[435]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[438]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[430]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[433]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[436]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[439]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[431]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[434]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[437]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[440]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[441]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[444]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[447]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[450]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[453]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[456]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[459]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[442]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[445]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[448]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[451]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[454]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[457]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[460]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[443]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[446]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[449]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[452]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[455]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[458]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[461]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[462]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[465]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[468]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[471]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[474]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[477]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[480]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[463]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[466]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[469]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[472]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[475]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[478]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[481]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[464]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[467]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[470]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[473]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[476]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[479]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[482]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[483]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[486]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[489]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[492]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[495]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[498]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[501]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[484]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[487]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[490]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[493]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[496]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[499]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[502]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[485]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[488]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[491]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[494]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[497]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[500]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[503]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[504]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[507]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[510]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[513]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[516]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[519]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[522]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[505]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[508]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[511]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[514]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[517]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[520]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[523]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[506]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[509]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[512]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[515]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[518]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[521]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[524]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[525]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[528]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[531]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[534]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[537]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[540]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[543]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[526]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[529]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[532]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[535]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[538]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[541]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[544]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[527]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[530]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[533]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[536]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[539]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[542]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[545]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[546]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[549]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[552]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[555]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[558]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[561]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[564]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[547]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[550]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[553]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[556]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[559]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[562]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[565]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[548]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[551]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[554]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[557]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[560]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[563]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[566]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[567]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[570]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[573]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[576]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[579]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[582]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[585]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[568]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[571]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[574]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[577]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[580]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[583]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[586]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[569]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[572]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[575]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[578]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[581]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[584]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[587]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[588]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[591]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[594]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[597]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[600]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[603]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[606]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[589]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[592]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[595]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[598]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[601]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[604]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[607]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[590]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[593]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[596]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[599]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[602]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[605]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[608]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[609]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[612]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[615]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[618]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[621]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[624]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[627]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[610]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[613]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[616]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[619]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[622]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[625]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[628]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[611]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[614]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[617]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[620]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[623]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[626]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[629]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[630]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[633]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[636]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[639]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[642]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[645]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[648]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[631]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[634]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[637]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[640]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[643]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[646]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[649]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[632]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[635]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[638]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[641]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[644]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[647]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[650]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[651]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[654]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[657]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[660]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[663]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[666]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[669]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[652]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[655]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[658]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[661]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[664]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[667]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[670]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[653]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[656]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[659]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[662]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[665]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[668]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[671]*kernel.shared_1[((threadIdx.x*96) + 95)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*8)) + 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)
}
}
}
@@ -394,7 +1226,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.310 ms
+ Execution time of this operator: 0.404 ms
@@ -442,36 +1274,36 @@ 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=4)
- conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
- conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+ 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=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
- conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+ conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
- conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=8)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+ 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=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
- compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
- compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+ 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)
@@ -491,14 +1323,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+ 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=8)
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=196)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
- s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+ s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -516,9 +1348,9 @@ 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__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
+ extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[672];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -527,58 +1359,822 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 8)] = (((((1 <= ((((((int)threadIdx.x) * 8) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) * 2) % 3)) - 8 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 3)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 6)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 256)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 257)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 257) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 258)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 259)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)b [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 260)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 260) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7 [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 261)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 262)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)b [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 263)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 11) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 11) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 263) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % [...]
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 512)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % [...]
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 20) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 28) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 12) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 44) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 52) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 132) {
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 20) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 513)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadI [...]
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 96)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 192)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 288)]));
- }
- }
- }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 514)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 10) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 10) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 514) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 515)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) + (ry_outer_outer * 7)) + (((int [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 516)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 4) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadI [...]
}
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 517)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 13) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 13) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 517) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 518)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) + (ry_outer_outer * 7)) + (((int [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 519)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 5) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadI [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[216] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[217] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[218] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[240] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[243] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[241] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[244] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[242] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[245] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[267] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[270] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[268] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[271] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[269] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[272] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[294] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[297] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[295] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[298] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[296] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[299] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[321] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[324] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[322] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[325] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[323] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[326] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[348] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[351] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[349] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[352] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[350] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[353] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[375] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[376] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[377] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[378] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[379] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[380] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[402] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[405] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[403] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[406] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[404] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[407] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[429] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[432] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[435] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[438] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[430] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[433] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[436] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[439] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[431] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[434] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[437] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[440] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[441] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[444] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[447] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[450] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[453] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[456] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[459] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[442] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[445] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[448] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[451] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[454] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[457] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[460] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[443] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[446] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[449] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[452] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[455] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[458] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[461] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[462] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[465] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[468] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[471] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[474] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[477] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[480] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[463] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[466] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[469] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[472] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[475] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[478] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[481] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[464] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[467] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[470] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[473] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[476] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[479] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[482] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[483] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[486] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[489] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[492] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[495] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[498] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[501] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[484] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[487] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[490] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[493] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[496] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[499] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[502] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[485] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[488] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[491] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[494] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[497] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[500] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[503] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[504] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[507] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[510] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[513] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[516] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[519] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[522] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[505] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[508] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[511] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[514] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[517] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[520] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[523] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[506] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[509] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[512] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[515] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[518] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[521] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[524] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[525] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[528] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[531] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[534] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[537] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[540] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[543] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[526] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[529] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[532] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[535] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[538] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[541] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[544] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[527] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[530] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[533] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[536] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[539] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[542] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[545] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[546] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[549] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[552] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[555] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[558] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[561] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[564] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[547] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[550] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[553] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[556] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[559] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[562] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[565] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[548] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[551] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[554] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[557] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[560] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[563] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[566] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[567] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[570] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[573] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[576] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[579] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[582] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[585] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[568] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[571] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[574] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[577] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[580] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[583] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[586] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[569] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[572] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[575] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[578] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[581] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[584] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[587] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[588] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[591] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[594] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[597] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[600] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[603] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[606] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[589] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[592] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[595] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[598] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[601] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[604] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[607] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[590] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[593] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[596] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[599] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[602] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[605] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[608] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[609] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[612] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[615] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[618] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[621] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[624] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[627] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[610] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[613] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[616] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[619] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[622] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[625] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[628] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[611] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[614] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[617] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[620] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[623] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[626] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[629] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[630] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[633] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[636] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[639] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[642] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[645] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[648] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[631] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[634] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[637] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[640] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[643] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[646] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[649] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[632] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[635] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[638] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[641] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[644] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[647] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[650] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[651] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[654] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[657] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[660] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[663] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[666] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[669] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[652] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[655] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[658] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[661] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[664] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[667] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[670] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[653] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[656] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[659] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[662] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[665] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[668] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[671] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 8)) + 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);
}
}
@@ -640,7 +2236,7 @@ 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 35.281 seconds)
+ **Total running time of the script:** ( 2 minutes 36.299 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 92a32a918..324e03dd2 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_cuda.rst.txt
@@ -646,7 +646,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5492 9.5289 9.5905 9.5283 0.0292
+ 10.1770 10.1816 10.2300 10.1194 0.0453
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 4684bf536..c909151cc 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_network_x86.rst.txt
@@ -665,7 +665,7 @@ so we can read the log file and load the best schedules.
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 754.7435 755.0369 755.3552 753.8383 0.6531
+ 756.4694 756.3174 758.9303 754.1606 1.9502
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 21.177 seconds)
+ **Total running time of the script:** ( 1 minutes 19.969 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 cb0477c36..f9a902980 100644
--- a/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
+++ b/docs/_sources/how_to/tune_with_autoscheduler/tune_sparse_x86.rst.txt
@@ -396,78 +396,27 @@ 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_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ 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: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*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
- }
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*512) + (i.outer.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 2) {
+ let cse_var_4: int32 = (((i0.outer*1024) + (i0.inner*512)) + (i1.outer*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -523,7 +472,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.719 ms
+ Execution time of this operator: 1.902 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 a5a85e06e..ffcaeaaef 100644
--- a/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:44.125** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.177** total execution time for **how_to_tune_with_autotvm** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:44.090 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.145 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_x86.py` (``tune_relay_x86.py``) | 00:00.019 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_relay_cuda.py` (``tune_relay_cuda.py``) | 00:00.005 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
index 784b3d29e..0aba27573 100644
--- a/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
+++ b/docs/_sources/how_to/tune_with_autotvm/tune_conv2d_cuda.rst.txt
@@ -879,8 +879,8 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
- No: 6 GFLOPS: 111.88/111.88 result: MeasureResult(costs=(0.002069203402597403,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8920879364013672, timestamp=1656083567.3411033) [('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: 0.00/111.88 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 109.11/109.11 result: MeasureResult(costs=(0.002121732916666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6635711193084717, timestamp=1656094762.5332358) [('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: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1003,7 +1003,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
- No: 8 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1126,7 +1126,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
- No: 9 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1249,7 +1249,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
- No: 10 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1267,7 +1267,7 @@ for this template
TimeoutError
[('tile_f', [-1, 32, 2, 4]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 4, 2]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4691833
- No: 11 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1390,7 +1390,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
- No: 12 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1513,7 +1513,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
- No: 13 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1636,7 +1636,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
- No: 14 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1759,7 +1759,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
- No: 15 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1882,7 +1882,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
- No: 16 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2005,7 +2005,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
- No: 17 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2128,7 +2128,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
- No: 18 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2251,7 +2251,7 @@ for this template
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
- No: 19 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2339,7 +2339,7 @@ for this template
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f01f7cfbfa2
+ 12: 0x00007f7e217a3fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2404,7 +2404,7 @@ for this template
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
- No: 20 GFLOPS: 144.04/144.04 result: MeasureResult(costs=(0.0016072552380952381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1629483699798584, timestamp=1656083593.7130096) [('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: 141.78/141.78 result: MeasureResult(costs=(0.0016327872741935482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1234588623046875, timestamp=1656094788.7532756) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
@@ -2461,7 +2461,7 @@ and measure running time.
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
- Time cost of this operator: 0.002005
+ Time cost of this operator: 0.002009
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 512344d2b..4a8cca93e 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_autotune.rst.txt
@@ -328,10 +328,10 @@ Timing the untuned program
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.678 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.259 1.036 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.286 (1, 1, 10, 10, 3) 1 1
- Total_time - 314.76 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.7 98.727 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.981 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.293 (1, 1, 10, 10, 3) 1 1
+ Total_time - 316.733 - - - -
@@ -397,10 +397,10 @@ Timing the tuned program
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
- tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 122.5 97.82 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.829 1.461 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.719 (1, 1, 10, 10, 3) 1 1
- Total_time - 125.23 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 192.2 98.556 (1, 1, 10, 10, 6) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.982 1.017 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.834 0.428 (1, 3, 10, 10, 1) 1 1
+ Total_time - 195.017 - - - -
diff --git a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
index 9475f64d5..828fdb2fb 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -225,7 +225,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmpcyl1ibri/images/random'
+ '/tmp/tmpcbeckp09/images/random'
@@ -325,8 +325,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmpcyl1ibri/images/target contains 8144 images
- /tmp/tmpcyl1ibri/images/random contains 5000 images
+ /tmp/tmpcbeckp09/images/target contains 8144 images
+ /tmp/tmpcbeckp09/images/random contains 5000 images
@@ -501,13 +501,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2194 - accuracy: 0.9229 - val_loss: 0.1428 - val_accuracy: 0.9558
+ 328/328 - 55s - loss: 0.2223 - accuracy: 0.9234 - val_loss: 0.1299 - val_accuracy: 0.9596
Epoch 2/3
- 328/328 - 52s - loss: 0.0956 - accuracy: 0.9650 - val_loss: 0.1064 - val_accuracy: 0.9656
+ 328/328 - 52s - loss: 0.1018 - accuracy: 0.9615 - val_loss: 0.1280 - val_accuracy: 0.9615
Epoch 3/3
- 328/328 - 52s - loss: 0.0637 - accuracy: 0.9767 - val_loss: 0.1252 - val_accuracy: 0.9619
+ 328/328 - 52s - loss: 0.0694 - accuracy: 0.9742 - val_loss: 0.1528 - val_accuracy: 0.9452
- <keras.callbacks.History object at 0x7f9d640bbbd0>
+ <keras.callbacks.History object at 0x7f675d8a59d0>
@@ -864,7 +864,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 7 minutes 40.201 seconds)
+ **Total running time of the script:** ( 7 minutes 59.583 seconds)
.. _sphx_glr_download_how_to_work_with_microtvm_micro_train.py:
diff --git a/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_microtvm/sg_execution_times.rst.txt
index 23527a6d9..da2bb2026 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
@@ -5,14 +5,14 @@
Computation times
=================
-**08:29.010** total execution time for **how_to_work_with_microtvm** files:
+**08:45.837** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 07:40.201 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 07:59.583 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:45.152 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.799 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.656 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.455 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_microtvm_micro_ethosu.py` (``micro_ethosu.py``) | 00:00.000 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
index 41ea663ac..f49b7d3c3 100644
--- a/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
+++ b/docs/_sources/how_to/work_with_relay/sg_execution_times.rst.txt
@@ -5,12 +5,12 @@
Computation times
=================
-**00:11.794** total execution time for **how_to_work_with_relay** files:
+**00:09.539** total execution time for **how_to_work_with_relay** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:10.225 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:08.075 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.564 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.459 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_how_to_work_with_relay_using_relay_viz.py` (``using_relay_viz.py``) | 00:00.006 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
index 8de6513c5..27f206fb3 100644
--- a/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/intrin_math.rst.txt
@@ -259,7 +259,7 @@ The following example customizes CUDA lowering rule for :code:`exp`.
.. code-block:: none
- <function my_cuda_math_rule at 0x7f9cbc9f79e0>
+ <function my_cuda_math_rule at 0x7f66d2f2fb90>
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 645f482f3..242df368d 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
@@ -5,22 +5,22 @@
Computation times
=================
-**00:04.299** total execution time for **how_to_work_with_schedules** files:
+**00:04.018** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.982 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.886 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:01.067 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.920 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.545 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.530 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.517 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.101 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.098 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.034 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_schedule_primitives.py` (``schedule_primitives.py``) | 00:00.033 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.027 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tedd.py` (``tedd.py``) | 00:00.028 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.012 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
index bb3dd3404..c778109a1 100644
--- a/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
+++ b/docs/_sources/how_to/work_with_schedules/tensorize.rst.txt
@@ -346,7 +346,7 @@ The importing needs to happen before the tensorized GEMV being executed.
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpnq81740h/input0.cc'\nsource_filename = \"/tmp/tmpnq81740h/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/tmpt4zzdkfh/input0.cc'\nsource_filename = \"/tmp/tmpt4zzdkfh/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 880c87cd3..5f4ee75e6 100644
--- a/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/autotvm/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:21.115** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:20.783** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:21.109 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.777 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.007 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_alu_vta.py` (``tune_alu_vta.py``) | 00:00.006 | 0.0 MB |
+---------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
index 36a44781e..bcad68249 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_classification.rst.txt
@@ -291,7 +291,7 @@ The compilation steps are:
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
- resnet18_v1 inference graph built in 22.96s!
+ resnet18_v1 inference graph built in 22.49s!
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 e5c6eb080..ed47328b3 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 16.12s!
+ yolov3-tiny inference graph built in 15.73s!
diff --git a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
index 0e8e5c9be..39ecf8611 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**01:31.474** total execution time for **topic_vta_tutorials_frontend** files:
+**01:30.302** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.266 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.768 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.208 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.534 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
index 793dba261..3a047f86b 100644
--- a/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/optimize/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:03.295** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.268** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.882 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.414 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.386 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
index 808861fa8..5e7769a32 100644
--- a/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/sg_execution_times.rst.txt
@@ -5,10 +5,10 @@
Computation times
=================
-**00:00.764** total execution time for **topic_vta_tutorials** files:
+**00:00.700** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.411 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.371 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.352 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.329 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
diff --git a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
index 0ae7f6686..9edd66a6b 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -327,7 +327,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 93.937 ms
+ Execution time of this operator: 93.341 ms
@@ -427,7 +427,7 @@ resume the status and do more 5 trials.
Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
- *E
+
@@ -443,11 +443,6 @@ Expression (TE) language that demonstrates how TVM can optimize computational
operations.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 3.242 seconds)
-
-
.. _sphx_glr_download_tutorial_auto_scheduler_matmul_x86.py:
.. only:: html
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 60b806348..d4141aa3a 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 9.62/9.62 result: MeasureResult(costs=(0.027897005600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5816020965576172, timestamp=1656082402.8525405) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.68/9.62 result: MeasureResult(costs=(0.100169451,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.744786024093628, timestamp=1656082404.6205306) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227596202,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5661830902099609, timestamp=1656082405.677771) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.86/11.79 result: MeasureResult(costs=(0.1442381726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4307260513305664, timestamp=1656082408.1538284) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.66/11.79 result: MeasureResult(costs=(0.07342711160000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3140251636505127, timestamp=1656082409.595319) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.70/11.79 result: MeasureResult(costs=(0.1578412646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.646113872528076, timestamp=1656082412.8173013) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.76/11.79 result: MeasureResult(costs=(0.3545529498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.789679288864136, timestamp=1656082419.1845098) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 9.83/11.79 result: MeasureResult(costs=(0.0273171538,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5848524570465088, timestamp=1656082419.786651) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.52/11.79 result: MeasureResult(costs=(0.1770291184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.944798707962036, timestamp=1656082422.8509488) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.18/11.79 result: MeasureResult(costs=(0.1232330916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0778651237487793, timestamp=1656082424.988339) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 10.34/10.34 result: MeasureResult(costs=(0.025971265799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5495269298553467, timestamp=1656093636.995069) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.65/10.34 result: MeasureResult(costs=(0.10123502820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.765075922012329, timestamp=1656093638.7738595) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022772455400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.55118727684021, timestamp=1656093639.8189595) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.56/11.79 result: MeasureResult(costs=(0.172348963,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8733017444610596, timestamp=1656093643.256166) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.60/11.79 result: MeasureResult(costs=(0.0744695276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3304519653320312, timestamp=1656093644.7122812) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.78/11.79 result: MeasureResult(costs=(0.15104362659999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.578220844268799, timestamp=1656093647.3361433) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.82/11.79 result: MeasureResult(costs=(0.3274878444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3515944480896, timestamp=1656093653.259746) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.04/11.79 result: MeasureResult(costs=(0.0267448458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762312412261963, timestamp=1656093653.84942) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.68/11.79 result: MeasureResult(costs=(0.1596127274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.651829481124878, timestamp=1656093656.6200204) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.26/11.79 result: MeasureResult(costs=(0.11855880939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.004706621170044, timestamp=1656093658.684421) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
diff --git a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
index a5b9f96c2..032c455b1 100644
--- a/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_relay_x86.rst.txt
@@ -314,7 +314,7 @@ standard deviation.
.. code-block:: none
- {'mean': 496.88231371000256, 'median': 496.1883234000197, 'std': 1.775787691602362}
+ {'mean': 497.09820047999983, 'median': 497.0073505500068, 'std': 0.594892070012249}
@@ -550,31 +550,31 @@ the tuning data to.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
-
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 5.90 s
[Task 1/25] Current/Best: 6.16/ 17.41 GFLOPS | Progress: (8/20) | 9.31 s
[Task 1/25] Current/Best: 11.54/ 22.68 GFLOPS | Progress: (12/20) | 11.75 s
[Task 1/25] Current/Best: 16.74/ 22.74 GFLOPS | Progress: (16/20) | 13.43 s
[Task 1/25] Current/Best: 11.58/ 23.87 GFLOPS | Progress: (20/20) | 15.16 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.18/ 12.91 GFLOPS | Progress: (4/20) | 3.78 s
[Task 2/25] Current/Best: 14.27/ 18.33 GFLOPS | Progress: (8/20) | 5.09 s
[Task 2/25] Current/Best: 21.24/ 21.24 GFLOPS | Progress: (12/20) | 6.40 s
[Task 2/25] Current/Best: 12.14/ 21.24 GFLOPS | Progress: (16/20) | 7.66 s
[Task 2/25] Current/Best: 19.25/ 21.24 GFLOPS | Progress: (20/20) | 9.23 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/ 10.52 GFLOPS | Progress: (4/20) | 5.90 s
[Task 3/25] Current/Best: 15.55/ 16.85 GFLOPS | Progress: (8/20) | 7.84 s
[Task 3/25] Current/Best: 14.85/ 16.85 GFLOPS | Progress: (12/20) | 9.55 s
[Task 3/25] Current/Best: 7.17/ 23.78 GFLOPS | Progress: (16/20) | 11.53 s
[Task 3/25] Current/Best: 12.62/ 23.78 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: 9.54/ 20.44 GFLOPS | Progress: (4/20) | 2.39 s
[Task 4/25] Current/Best: 6.65/ 20.44 GFLOPS | Progress: (8/20) | 6.74 s
[Task 4/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 11.32 s
[Task 4/25] Current/Best: 16.52/ 21.35 GFLOPS | Progress: (16/20) | 13.58 s
[Task 4/25] Current/Best: 13.29/ 21.35 GFLOPS | Progress: (20/20) | 15.48 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.45/ 10.12 GFLOPS | Progress: (4/20) | 2.60 s
[Task 5/25] Current/Best: 11.53/ 11.83 GFLOPS | Progress: (8/20) | 4.68 s
[Task 5/25] Current/Best: 10.14/ 18.04 GFLOPS | Progress: (12/20) | 7.63 s
[Task 5/25] Current/Best: 11.67/ 22.42 GFLOPS | Progress: (16/20) | 9.07 s
[Task 5/25] Current/Best: 11.86/ 22.42 GFLOPS | Progress: (20/20) | 10.95 s Done.
-
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.68 GFLOPS | Progress: (4/20) | 3.99 s
[Task 6/25] Current/Best: 18.94/ 20.68 GFLOPS | Progress: (8/20) | 5.75 s
[Task 6/25] Current/Best: 13.14/ 20.68 GFLOPS | Progress: (12/20) | 7.68 s
[Task 6/25] Current/Best: 19.76/ 20.68 GFLOPS | Progress: (16/20) | 9.93 s
[Task 6/25] Current/Best: 3.72/ 20.68 GFLOPS | Progress: (20/20) | 12.47 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.19/ 12.78 GFLOPS | Progress: (4/20) | 3.57 s
[Task 7/25] Current/Best: 20.20/ 21.06 GFLOPS | Progress: (8/20) | 5.08 s
[Task 7/25] Current/Best: 16.04/ 21.06 GFLOPS | Progress: (12/20) | 7.00 s
[Task 7/25] Current/Best: 12.25/ 21.06 GFLOPS | Progress: (16/20) | 9.05 s
[Task 7/25] Current/Best: 6.33/ 21.69 GFLOPS | Progress: (20/20) | 11.51 s Done.
-
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.83/ 14.38 GFLOPS | Progress: (4/20) | 2.96 s
[Task 8/25] Current/Best: 9.68/ 14.38 GFLOPS | Progress: (8/20) | 7.78 s
[Task 8/25] Current/Best: 13.18/ 14.38 GFLOPS | Progress: (12/20) | 13.96 s
[Task 8/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (16/20) | 16.05 s
[Task 8/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 22.56 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.27/ 15.66 GFLOPS | Progress: (4/20) | 11.97 s
[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.79 s
[Task 9/25] Current/Best: 8.25/ 23.47 GFLOPS | Progress: (12/20) | 16.16 s
[Task 9/25] Current/Best: 17.93/ 23.47 GFLOPS | Progress: (16/20) | 18.79 s
[Task 9/25] Current/Best: 8.98/ 23.47 GFLOPS | Progress: (20/20) | 26.40 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (4/20) | 2.59 s
[Task 10/25] Current/Best: 15.29/ 18.27 GFLOPS | Progress: (8/20) | 4.16 s
[Task 10/25] Current/Best: 12.30/ 19.02 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.06/ 20.12 GFLOPS | Progress: (16/20) | 6.79 s
[Task 10/25] Current/Best: 8.89/ 20.12 GFLOPS | Progress: (20/20
) | 8.34 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.28/ 18.16 GFLOPS | Progress: (4/20) | 3.28 s
[Task 11/25] Current/Best: 16.64/ 18.16 GFLOPS | Progress: (8/20) | 5.99 s
[Task 11/25] Current/Best: 17.98/ 18.16 GFLOPS | Progress: (12/20) | 8.00 s
[Task 11/25] Current/Best: 13.41/ 21.21 GFLOPS | Progress: (16/20) | 10.79 s
[Task 11/25] Current/Best: 19.32/ 21.54 GFLOPS | Progress: (20/20) | 12.82 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.82/ 17.99 GFLOPS | Progress: (4/20) | 5.37 s
[Task 12/25] Current/Best: 5.22/ 17.99 GFLOPS | Progress: (8/20) | 9.10 s
[Task 12/25] Current/Best: 18.76/ 18.98 GFLOPS | Progress: (12/20) | 11.08 s
[Task 12/25] Current/Best: 15.37/ 18.98 GFLOPS | Progress: (16/20) | 13.82 s
[Task 12/25] Current/Best: 15.12/ 18.98 GFLOPS | Progress: (20/20) | 15.74 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.87/ 17.34 GFLOPS | Progress: (4/20) | 3.66 s
[Task 13/25] Current/Best: 15.12/ 20.96 GFLOPS | Progress: (8/20) | 6.11 s
[Task 13/25] Current/Best: 19.59/ 21.65 GFLOPS | Progress: (12/20) | 9.02 s
[Task 13/25] Current/Best: 12.23/ 21.65 GFLOPS | Progress: (16/20) | 12.39 s
[Task 13/25] Current/Best: 18.64/ 21.65 GFLOPS | Progress: (20/20) | 14.67 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.32 s
[Task 14/25] Current/Best: 6.11/ 13.60 GFLOPS | Progress: (8/20) | 5.49 s
[Task 14/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (12/20) | 8.03 s
[Task 14/25] Current/Best: 16.19/ 20.08 GFLOPS | Progress: (16/20) | 9.69 s Done.
-
[Task 14/25] Current/Best: 17.11/ 20.08 GFLOPS | Progress: (20/20) | 11.47 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.12/ 17.59 GFLOPS | Progress: (4/20) | 2.77 s
[Task 15/25] Current/Best: 14.28/ 18.12 GFLOPS | Progress: (8/20) | 4.12 s
[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.21 s
[Task 15/25] Current/Best: 20.38/ 22.28 GFLOPS | Progress: (16/20) | 9.16 s
[Task 15/25] Current/Best: 9.64/ 22.28 GFLOPS | Progress: (20/20) | 10.13 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (4/20) | 3.06 s
[Task 16/25] Current/Best: 3.04/ 20.69 GFLOPS | Progress: (8/20) | 4.71 s
[Task 16/25] Current/Best: 19.76/ 20.69 GFLOPS | Progress: (12/20) | 5.93 s
[Task 16/25] Current/Best: 17.22/ 20.69 GFLOPS | Progress: (16/20) |
7.30 s
[Task 16/25] Current/Best: 10.12/ 22.27 GFLOPS | Progress: (20/20) | 9.34 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.42/ 18.84 GFLOPS | Progress: (4/20) | 4.70 s
[Task 17/25] Current/Best: 14.38/ 23.00 GFLOPS | Progress: (8/20) | 7.48 s
[Task 17/25] Current/Best: 16.75/ 23.00 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 16.44/ 23.00 GFLOPS | Progress: (16/20) | 11.66 s
[Task 17/25] Current/Best: 10.03/ 23.00 GFLOPS | Progress: (20/20) | 13.80 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.25/ 17.09 GFLOPS | Progress: (4/20) | 3.74 s
[Task 18/25] Current/Best: 10.59/ 19.53 GFLOPS | Progress: (8/20) | 7.26 s
[Task 18/25] Current/Best: 19.27/ 19.53 GFLOPS | Progress: (12/20) | 9.21 s
[Task 18/25] Current/Best: 10.02/ 19.53 GFLOPS | Progress: (16/20) | 12.83 s
[Task 18/25] Current/Best: 20.67/ 20.67 GFLOPS | Progress: (20/20) | 14.37 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.14/ 20.12 GFLOPS | Progress: (4/20) | 6.06 s
[Task 19/25] Current/Best: 2.60/ 20.12 GFLOPS | Progress: (8/20) | 9.31 s
[Task 19/25] Current/Best: 19.20/ 20.93 GFLOPS | Progress: (12/20) | 12.07 s
[Task 19/25] Current/Best: 15.34/ 21.68 GFLOPS | Progress: (16/20) | 14.91 s
[Task 19/25] Current/Best: 2.70/ 23.45 GFLOPS | Progress: (20/20) | 17.68 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 8.79/ 14.94 GFLOPS | Progress: (4/20) | 3.34 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 6.25 s
[Task 1/25] Current/Best: 6.17/ 17.42 GFLOPS | Progress: (8/20) | 9.22 s
[Task 1/25] Current/Best: 11.55/ 22.81 GFLOPS | Progress: (12/20) | 11.63 s
[Task 1/25] Current/Best: 16.86/ 22.81 GFLOPS | Progress: (16/20) | 13.31 s
[Task 1/25] Current/Best: 11.63/ 23.87 GFLOPS | Progress: (20/20) | 15.05 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.18/ 13.11 GFLOPS | Progress: (4/20) | 3.63 s
[Task 2/25] Current/Best: 13.96/ 18.31 GFLOPS | Progress: (8/20) | 4.93 s
[Task 2/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (12/20) | 6.24 s
[Task 2/25] Current/Best: 11.69/ 21.21 GFLOPS | Progress: (16/20) | 7.54 s
[Task 2/25] Current/Best: 19.08/ 21.21 GFLOPS | Progress: (20/20) | 9.14 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/ 10.60 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.51/ 16.83 GFLOPS | Progress: (8/20) | 7.78 s
[Task 3/25] Current/Best: 14.86/ 16.83 GFLOPS | Progress: (12/20) | 9.50 s
[Task 3/25] Current/Best: 7.19/ 23.81 GFLOPS | Progress: (16/20) | 11.45 s
[Task 3/25] Current/Best: 12.55/ 23.81 GFLOPS | Progress: (20/20) | 15.95 s Done.
+
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.56/ 20.46 GFLOPS | Progress: (4/20) | 2.37 s
[Task 4/25] Current/Best: 6.75/ 20.46 GFLOPS | Progress: (8/20) | 6.71 s
[Task 4/25] Current/Best: 22.08/ 22.08 GFLOPS | Progress: (12/20) | 11.21 s
[Task 4/25] Current/Best: 17.35/ 22.08 GFLOPS | Progress: (16/20) | 13.45 s
[Task 4/25] Current/Best: 13.18/ 22.08 GFLOPS | Progress: (20/20) | 15.42 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.35/ 10.31 GFLOPS | Progress: (4/20) | 2.58 s
[Task 5/25] Current/Best: 11.53/ 12.40 GFLOPS | Progress: (8/20) | 4.66 s
[Task 5/25] Current/Best: 11.55/ 17.68 GFLOPS | Progress: (12/20) | 7.73 s
[Task 5/25] Current/Best: 11.69/ 22.86 GFLOPS | Progress: (16/20) | 9.14 s
[Task 5/25] Current/Best: 12.01/ 22.86 GFLOPS | Progress: (20/20) | 11.02 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.21/ 20.70 GFLOPS | Progress: (4/20) | 3.98 s
[Task 6/25] Current/Best: 18.85/ 20.70 GFLOPS | Progress: (8/20) | 5.74 s
[Task 6/25] Current/Best: 13.28/ 20.70 GFLOPS | Progress: (12/20) | 7.66 s
[Task 6/25] Current/Best: 19.84/ 20.70 GFLOPS | Progress: (16/20) | 9.94 s
[Task 6/25] Current/Best: 3.69/ 20.70 GFLOPS | Progress: (20/20) | 12.48 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.19/ 12.92 GFLOPS | Progress: (4/20) | 3.53 s
[Task 7/25] Current/Best: 20.31/ 21.04 GFLOPS | Progress: (8/20) | 5.03 s
[Task 7/25] Current/Best: 16.12/ 21.04 GFLOPS | Progress: (12/20) | 6.98 s
[Task 7/25] Current/Best: 12.19/ 21.04 GFLOPS | Progress: (16/20) | 9.01 s
[Task 7/25] Current/Best: 6.36/ 21.72 GFLOPS | Progress: (20/20) | 11.47 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.64/ 14.07 GFLOPS | Progress: (4/20) | 2.91 s
[Task 8/25] Current/Best: 9.42/ 14.07 GFLOPS | Progress: (8/20) | 7.75 s
[Task 8/25] Current/Best: 12.51/ 14.07 GFLOPS | Progress: (12/20) | 13.96 s
[Task 8/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (16/20) | 16.05 s
[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (20/20) | 22.52 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.27/ 15.83 GFLOPS | Progress: (4/20) | 11.94 s
[Task 9/25] Current/Best: 23.53/ 23.53 GFLOPS | Progress: (8/20) | 13.74 s
[Task 9/25] Current/Best: 8.22/ 23.53 GFLOPS | Progress: (12/20) | 16.11 s
[Task 9/25] Current/Best: 17.89/ 23.53 GFLOPS | Progress: (16/20) | 18.77 s
[Task 9/25] Current/Best: 9.02/ 23.53 GFLOPS | Progress: (20/20) | 26.30 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.57 s
[Task 10/25] Current/Best: 15.53/ 18.23 GFLOPS | Progress: (8/20) | 4.14 s
[Task 10/25] Current/Best: 11.99/ 18.88 GFLOPS | Progress: (12/20) | 5.66 s
[Task 10/25] Current/Best: 18.60/ 20.50 GFLOPS | Progress: (16/20) | 6.77 s
[Task 10/25] Current/Best: 8.80/ 20.50 GFLOPS | Progress: (20/20
) | 8.32 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 11.13/ 18.14 GFLOPS | Progress: (4/20) | 3.33 s
[Task 11/25] Current/Best: 16.57/ 18.14 GFLOPS | Progress: (8/20) | 6.04 s
[Task 11/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 8.07 s
[Task 11/25] Current/Best: 13.45/ 21.19 GFLOPS | Progress: (16/20) | 10.84 s
[Task 11/25] Current/Best: 19.45/ 21.41 GFLOPS | Progress: (20/20) | 12.89 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/ 18.03 GFLOPS | Progress: (4/20) | 5.44 s
[Task 12/25] Current/Best: 5.22/ 18.03 GFLOPS | Progress: (8/20) | 9.14 s
[Task 12/25] Current/Best: 18.93/ 18.98 GFLOPS | Progress: (12/20) | 11.14 s
[Task 12/25] Current/Best: 15.16/ 18.98 GFLOPS | Progress: (16/20) | 13.94 s
[Task 12/25] Current/Best: 15.12/ 19.06 GFLOPS | Progress: (20/20) | 15.86 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.65/ 17.37 GFLOPS | Progress: (4/20) | 3.68 s
[Task 13/25] Current/Best: 15.96/ 20.92 GFLOPS | Progress: (8/20) | 6.09 s
[Task 13/25] Current/Best: 19.62/ 21.66 GFLOPS | Progress: (12/20) | 8.95 s
[Task 13/25] Current/Best: 12.23/ 21.66 GFLOPS | Progress: (16/20) | 12.31 s
[Task 13/25] Current/Best: 18.57/ 21.66 GFLOPS | Progress: (20/20) | 14.53 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.65/ 13.65 GFLOPS | Progress: (4/20) | 3.28 s
[Task 14/25] Current/Best: 6.08/ 13.65 GFLOPS | Progress: (8/20) | 5.49 s
[Task 14/25] Current/Best: 20.77/ 20.77 GFLOPS | Progress: (12/20) | 8.01 s
[Task 14/25] Current/Best: 16.19/ 20.77 GFLOPS | Progress: (16/20) | 9.65 s Done.
+
[Task 14/25] Current/Best: 17.20/ 20.77 GFLOPS | Progress: (20/20) | 11.36 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.20/ 17.63 GFLOPS | Progress: (4/20) | 2.70 s
[Task 15/25] Current/Best: 14.45/ 18.13 GFLOPS | Progress: (8/20) | 4.03 s
[Task 15/25] Current/Best: 10.38/ 22.19 GFLOPS | Progress: (12/20) | 6.09 s
[Task 15/25] Current/Best: 20.40/ 22.19 GFLOPS | Progress: (16/20) | 9.42 s
[Task 15/25] Current/Best: 9.70/ 22.19 GFLOPS | Progress: (20/20) | 10.44 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (4/20) | 2.97 s
[Task 16/25] Current/Best: 3.04/ 20.47 GFLOPS | Progress: (8/20) | 4.58 s
[Task 16/25] Current/Best: 19.58/ 20.47 GFLOPS | Progress: (12/20) | 5.81 s
[Task 16/25] Current/Best: 18.06/ 20.47 GFLOPS | Progress: (16/20) |
7.15 s
[Task 16/25] Current/Best: 9.98/ 22.33 GFLOPS | Progress: (20/20) | 9.19 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.31/ 16.81 GFLOPS | Progress: (4/20) | 4.71 s
[Task 17/25] Current/Best: 14.39/ 23.25 GFLOPS | Progress: (8/20) | 7.55 s
[Task 17/25] Current/Best: 16.84/ 23.25 GFLOPS | Progress: (12/20) | 9.60 s
[Task 17/25] Current/Best: 16.41/ 23.25 GFLOPS | Progress: (16/20) | 11.75 s
[Task 17/25] Current/Best: 10.02/ 23.25 GFLOPS | Progress: (20/20) | 13.87 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 10.99/ 17.85 GFLOPS | Progress: (4/20) | 3.69 s
[Task 18/25] Current/Best: 10.55/ 17.85 GFLOPS | Progress: (8/20) | 7.22 s
[Task 18/25] Current/Best: 19.17/ 19.17 GFLOPS | Progress: (12/20) | 9.14 s
[Task 18/25] Current/Best: 9.95/ 19.17 GFLOPS | Progress: (16/20) | 12.68 s
[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.20 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.14/ 20.26 GFLOPS | Progress: (4/20) | 6.10 s
[Task 19/25] Current/Best: 2.61/ 20.26 GFLOPS | Progress: (8/20) | 9.36 s
[Task 19/25] Current/Best: 19.71/ 21.86 GFLOPS | Progress: (12/20) | 12.09 s
[Task 19/25] Current/Best: 15.07/ 22.26 GFLOPS | Progress: (16/20) | 14.91 s
[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 17.72 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.24/ 15.13 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-
[Task 20/25] Current/Best: 9.97/ 14.94 GFLOPS | Progress: (8/20) | 6.65 s
[Task 20/25] Current/Best: 2.32/ 16.65 GFLOPS | Progress: (12/20) | 10.81 s
[Task 20/25] Current/Best: 12.35/ 16.65 GFLOPS | Progress: (16/20) | 14.38 s
[Task 20/25] Current/Best: 13.68/ 21.72 GFLOPS | Progress: (20/20) | 16.47 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.39/ 17.70 GFLOPS | Progress: (4/20) | 3.25 s
[Task 21/25] Current/Best: 14.54/ 17.70 GFLOPS | Progress: (8/20) | 4.83 s
[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.00 s
[Task 21/25] Current/Best: 17.92/ 17.92 GFLOPS | Progress: (16/20) | 10.45 s
[Task 21/25] Current/Best: 4.46/ 17.92 GFLOPS | Progress: (20/20) | 17.67 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 16.63 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 8.67/ 22.00 GFLOPS | Progress: (8/20) | 4.59 s
[Task 22/25] Current/Best: 20.02/ 22.00 GFLOPS | Progress: (12/20) | 6.88 s
[Task 22/25] Current/Best: 14.91/ 22.00 GFLOPS | Progress: (16/20) | 8.96 s
[Task 22/25] Current/Best: 14.07/ 22.00 GFLOPS | Progress: (20/20) | 10.67 s Done.
-
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.35/ 20.26 GFLOPS | Progress: (4/20) | 3.27 s
[Task 23/25] Current/Best: 14.43/ 20.26 GFLOPS | Progress: (8/20) | 6.54 s
[Task 23/25] Current/Best: 20.88/ 21.31 GFLOPS | Progress: (12/20) | 8.36 s
[Task 23/25] Current/Best: 6.42/ 21.31 GFLOPS | Progress: (16/20) | 15.43 s
[Task 23/25] Current/Best: 7.76/ 21.31 GFLOPS | Progress: (20/20) | 19.64 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.33/ 8.33 GFLOPS | Progress: (4/20) | 11.80 s
[Task 24/25] Current/Best: 1.97/ 8.33 GFLOPS | Progress: (8/20) | 22.81 s
[Task 24/25] Current/Best: 4.09/ 8.33 GFLOPS | Progress: (12/20) | 34.37 s Done.
+
[Task 20/25] Current/Best: 10.40/ 15.13 GFLOPS | Progress: (8/20) | 6.76 s
[Task 20/25] Current/Best: 2.32/ 16.65 GFLOPS | Progress: (12/20) | 10.61 s
[Task 20/25] Current/Best: 12.40/ 16.65 GFLOPS | Progress: (16/20) | 14.15 s
[Task 20/25] Current/Best: 11.53/ 22.15 GFLOPS | Progress: (20/20) | 16.27 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.42/ 17.70 GFLOPS | Progress: (4/20) | 3.23 s
[Task 21/25] Current/Best: 14.64/ 17.70 GFLOPS | Progress: (8/20) | 4.80 s
[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 6.95 s
[Task 21/25] Current/Best: 17.89/ 17.89 GFLOPS | Progress: (16/20) | 10.38 s
[Task 21/25] Current/Best: 4.47/ 17.89 GFLOPS | Progress: (20/20) | 17.48 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.07 GFLOPS | Progress: (4/20
) | 2.66 s
[Task 22/25] Current/Best: 8.66/ 21.79 GFLOPS | Progress: (8/20) | 4.65 s
[Task 22/25] Current/Best: 19.98/ 21.79 GFLOPS | Progress: (12/20) | 6.94 s
[Task 22/25] Current/Best: 15.47/ 21.79 GFLOPS | Progress: (16/20) | 8.98 s
[Task 22/25] Current/Best: 14.57/ 21.79 GFLOPS | Progress: (20/20) | 10.63 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.51/ 20.34 GFLOPS | Progress: (4/20) | 3.25 s
[Task 23/25] Current/Best: 15.03/ 20.34 GFLOPS | Progress: (8/20) | 6.59 s
[Task 23/25] Current/Best: 20.97/ 21.45 GFLOPS | Progress: (12/20) | 8.38 s
[Task 23/25] Current/Best: 6.41/ 21.45 GFLOPS | Progress: (16/20) | 15.40 s
[Task 23/25] Current/Best: 7.86/ 21.45 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: 8.47/ 8.47 GFLOPS | Progress: (4/20) | 11.79 s
[Task 24/25] Current/Best: 3.51/ 8.47 GFLOPS | Progress: (8/20) | 23.02 s
[Task 24/25] Current/Best: 4.24/ 8.47 GFLOPS | Progress: (12/20) | 33.77 s Done.
Done.
-
[Task 24/25] Current/Best: 6.09/ 8.70 GFLOPS | Progress: (16/20) | 39.84 s
[Task 24/25] Current/Best: 3.25/ 8.84 GFLOPS | Progress: (20/20) | 45.76 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/ 2.81 GFLOPS | Progress: (4/20) | 11.61 s
[Task 25/25] Current/Best: 5.80/ 7.86 GFLOPS | Progress: (8/20) | 22.89 s
[Task 25/25] Current/Best: 6.01/ 7.86 GFLOPS | Progress: (12/20) | 34.17 s
[Task 25/25] Current/Best: 5.73/ 8.87 GFLOPS | Progress: (16/20) | 35.89 s
[Task 25/25] Current/Best: 2.95/ 8.87 GFLOPS | Progress: (20/20) | 46.60 s
+
[Task 24/25] Current/Best: 6.15/ 8.93 GFLOPS | Progress: (16/20) | 39.22 s
[Task 24/25] Current/Best: 3.35/ 8.93 GFLOPS | Progress: (20/20) | 45.21 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/ 2.75 GFLOPS | Progress: (4/20) | 11.58 s
[Task 25/25] Current/Best: 5.85/ 8.14 GFLOPS | Progress: (8/20) | 22.83 s
[Task 25/25] Current/Best: 6.00/ 8.14 GFLOPS | Progress: (12/20) | 34.11 s
[Task 25/25] Current/Best: 5.82/ 8.35 GFLOPS | Progress: (16/20) | 35.85 s
[Task 25/25] Current/Best: 2.84/ 8.72 GFLOPS | Progress: (20/20) | 46.52 s
@@ -677,8 +677,8 @@ Verify that the optimized model runs and produces the same results:
.. code-block:: none
- class='n02123045 tabby, tabby cat' with probability=0.621104
- class='n02123159 tiger cat' with probability=0.356378
+ class='n02123045 tabby, tabby cat' with probability=0.621105
+ class='n02123159 tiger cat' with probability=0.356377
class='n02124075 Egyptian cat' with probability=0.019712
class='n02129604 tiger, Panthera tigris' with probability=0.001215
class='n04040759 radiator' with probability=0.000262
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 410.28751223000654, 'median': 410.1254887000323, 'std': 0.7726162332792078}
- unoptimized: {'mean': 496.88231371000256, 'median': 496.1883234000197, 'std': 1.775787691602362}
+ optimized: {'mean': 413.1419657599963, 'median': 413.0868064499964, 'std': 0.6840461854077801}
+ unoptimized: {'mean': 497.09820047999983, 'median': 497.0073505500068, 'std': 0.594892070012249}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 16.015 seconds)
+ **Total running time of the script:** ( 10 minutes 13.278 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 e1e385135..6518d76b6 100644
--- a/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
+++ b/docs/_sources/tutorial/cross_compilation_and_rpc.rst.txt
@@ -269,7 +269,7 @@ device and returns the measured cost. Network overhead is excluded.
.. code-block:: none
- 1.289e-07 secs/op
+ 1.3e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 78505420a..b7e94b5c5 100644
--- a/docs/_sources/tutorial/intro_topi.rst.txt
+++ b/docs/_sources/tutorial/intro_topi.rst.txt
@@ -262,7 +262,7 @@ As you can see, scheduled stages of computation have been accumulated and we can
.. code-block:: none
- [stage(a, placeholder(a, 0x10aa4440)), stage(b, placeholder(b, 0x233ac910)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
+ [stage(a, placeholder(a, 0x21541620)), stage(b, placeholder(b, 0x22863260)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(mi [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index a0957d5c7..f06cd090f 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,29 +5,29 @@
Computation times
=================
-**13:16.550** total execution time for **tutorial** files:
+**12:56.859** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:16.015 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:13.278 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 01:03.242 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:59.974 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.606 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.089 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.383 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.035 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.670 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:25.139 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.789 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.676 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.681 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.515 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.164 | 0.0 MB |
-+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.152 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
+| :ref:`sphx_glr_tutorial_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
++------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_tvmc_python.py` (``tvmc_python.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_install.py` (``install.py``) | 00:00.000 | 0.0 MB |
diff --git a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
index ef4969aae..3f1788c78 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -288,7 +288,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
- Numpy running time: 0.000009
+ Numpy running time: 0.000010
naive: 0.000006
@@ -390,7 +390,7 @@ compile and run this new schedule with the parallel operation applied:
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallel: 0.000007
+ parallel: 0.000006
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 9.290320003856322e-06 1.0
- naive 5.8558e-06 0.6303119803805804
- parallel 6.937e-06 0.7466911793264945
- vector 2.4806e-05 2.6700910183613984
+ numpy 9.969230000024254e-06 1.0
+ naive 5.8628e-06 0.588089551548689
+ parallel 6.1027e-06 0.6121535966153006
+ vector 2.4564299999999998e-05 2.4640117641924437
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018710
+ Numpy running time: 0.018899
@@ -983,7 +983,7 @@ optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- none: 3.441191
+ none: 3.338866
@@ -1088,7 +1088,7 @@ schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- blocking: 0.314293
+ blocking: 0.304134
@@ -1186,7 +1186,7 @@ already cache friendly from our previous optimizations.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- vectorization: 0.352376
+ vectorization: 0.339931
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1262,7 +1262,7 @@ more cache friendly.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- loop permutation: 0.118407
+ loop permutation: 0.114518
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1363,7 +1363,7 @@ optimized schedule.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- array packing: 0.109070
+ array packing: 0.108645
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1458,7 +1458,7 @@ to `C` when all the block results are ready.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- block caching: 0.110747
+ block caching: 0.111016
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1546,7 +1546,7 @@ of thread-level parallelization.
/workspace/python/tvm/driver/build_module.py:264: UserWarning: target_host parameter is going to be deprecated. Please pass in tvm.target.Target(target, host=target_host) instead.
"target_host parameter is going to be deprecated. "
- parallelization: 0.142808
+ parallelization: 0.144471
@main = primfn(A_1: handle, B_1: handle, C_1: handle) -> ()
attr = {"from_legacy_te_schedule": True, "global_symbol": "main", "tir.noalias": True}
buffers = {A: Buffer(A_2: Pointer(float32), float32, [1048576], []),
@@ -1627,13 +1627,13 @@ working, we can compare the results.
.. code-block:: none
Operator Timing Performance
- none 3.4411908497 1.0
- blocking 0.31429253370000004 0.09133249140407304
- vectorization 0.3523756119 0.10239932258645865
- loop permutation 0.1184072601 0.034408803600742645
- array packing 0.10906975000000001 0.03169535046552522
- block caching 0.11074662269999999 0.03218264476951483
- parallelization 0.142808014 0.04149959134421443
+ none 3.3388662441999997 1.0
+ blocking 0.30413420599999996 0.09108906549590495
+ vectorization 0.3399305729 0.10181017987482999
+ loop permutation 0.1145181479 0.03429851318510629
+ array packing 0.108644995 0.03253948707550925
+ block caching 0.1110158872 0.03324957607776219
+ parallelization 0.1444712218 0.043269544579979315
@@ -1673,11 +1673,6 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
-.. rst-class:: sphx-glr-timing
-
- **Total running time of the script:** ( 1 minutes 1.606 seconds)
-
-
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 088505eb9..fe90e12c8 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-ed3294fb3fca996e4a75151974f0d4784c0d8693
+f1d30a27b2efe5b15e6492f785be1d41c9a75ab9
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index b9c03adca..29109cd4e 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -422,7 +422,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip486fd0a7-e584-4908-96b1-cf7c8949d1b2 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7711d7c2-bb2d-4ab9-b495-a12f8fe83ee8 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 a5f1097f1..91c1a3cb6 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -427,96 +427,41 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<09:48, 73.9kB/s]
- 0%| | 40.0k/41.5M [00:00<07:31, 96.2kB/s]
- 0%| | 96.0k/41.5M [00:00<03:59, 181kB/s]
- 0%| | 160k/41.5M [00:00<02:55, 248kB/s]
- 1%| | 328k/41.5M [00:01<01:31, 474kB/s]
- 1%|1 | 536k/41.5M [00:01<01:05, 652kB/s]
- 2%|1 | 744k/41.5M [00:01<00:56, 756kB/s]
- 2%|2 | 952k/41.5M [00:01<00:51, 829kB/s]
- 3%|2 | 1.13M/41.5M [00:01<00:47, 899kB/s]
- 3%|3 | 1.34M/41.5M [00:02<00:44, 946kB/s]
- 4%|3 | 1.54M/41.5M [00:02<00:44, 949kB/s]
- 4%|4 | 1.74M/41.5M [00:02<00:43, 952kB/s]
- 5%|4 | 1.95M/41.5M [00:02<00:42, 966kB/s]
- 5%|5 | 2.16M/41.5M [00:02<00:40, 1.01MB/s]
- 6%|5 | 2.37M/41.5M [00:03<00:38, 1.06MB/s]
- 6%|6 | 2.58M/41.5M [00:03<00:39, 1.03MB/s]
- 7%|6 | 2.79M/41.5M [00:03<00:39, 1.02MB/s]
- 7%|7 | 3.00M/41.5M [00:03<00:39, 1.01MB/s]
- 8%|7 | 3.21M/41.5M [00:03<00:38, 1.05MB/s]
- 8%|8 | 3.43M/41.5M [00:04<00:36, 1.09MB/s]
- 9%|8 | 3.66M/41.5M [00:04<00:36, 1.08MB/s]
- 9%|9 | 3.88M/41.5M [00:04<00:37, 1.07MB/s]
- 10%|9 | 4.11M/41.5M [00:04<00:35, 1.09MB/s]
- 10%|# | 4.34M/41.5M [00:05<00:34, 1.14MB/s]
- 11%|#1 | 4.58M/41.5M [00:05<00:33, 1.16MB/s]
- 12%|#1 | 4.81M/41.5M [00:05<00:27, 1.38MB/s]
- 12%|#1 | 4.96M/41.5M [00:05<00:28, 1.35MB/s]
- 12%|#2 | 5.10M/41.5M [00:05<00:34, 1.09MB/s]
- 13%|#2 | 5.33M/41.5M [00:05<00:34, 1.10MB/s]
- 13%|#3 | 5.59M/41.5M [00:06<00:31, 1.20MB/s]
- 14%|#4 | 5.87M/41.5M [00:06<00:29, 1.27MB/s]
- 15%|#4 | 6.13M/41.5M [00:06<00:24, 1.51MB/s]
- 15%|#5 | 6.30M/41.5M [00:06<00:25, 1.45MB/s]
- 16%|#5 | 6.45M/41.5M [00:06<00:31, 1.17MB/s]
- 16%|#6 | 6.74M/41.5M [00:06<00:27, 1.33MB/s]
- 17%|#7 | 7.06M/41.5M [00:07<00:24, 1.45MB/s]
- 18%|#7 | 7.38M/41.5M [00:07<00:19, 1.80MB/s]
- 18%|#8 | 7.58M/41.5M [00:07<00:20, 1.70MB/s]
- 19%|#8 | 7.76M/41.5M [00:07<00:25, 1.38MB/s]
- 20%|#9 | 8.10M/41.5M [00:07<00:22, 1.53MB/s]
- 20%|## | 8.47M/41.5M [00:07<00:17, 1.95MB/s]
- 21%|## | 8.69M/41.5M [00:08<00:18, 1.89MB/s]
- 21%|##1 | 8.89M/41.5M [00:08<00:21, 1.59MB/s]
- 22%|##2 | 9.28M/41.5M [00:08<00:19, 1.76MB/s]
- 23%|##3 | 9.70M/41.5M [00:08<00:15, 2.22MB/s]
- 24%|##3 | 9.94M/41.5M [00:08<00:15, 2.10MB/s]
- 24%|##4 | 10.2M/41.5M [00:08<00:18, 1.76MB/s]
- 26%|##5 | 10.6M/41.5M [00:09<00:16, 2.00MB/s]
- 27%|##6 | 11.1M/41.5M [00:09<00:14, 2.21MB/s]
- 28%|##7 | 11.6M/41.5M [00:09<00:13, 2.25MB/s]
- 29%|##9 | 12.1M/41.5M [00:09<00:13, 2.35MB/s]
- 31%|### | 12.7M/41.5M [00:09<00:10, 2.94MB/s]
- 31%|###1 | 13.0M/41.5M [00:09<00:10, 2.84MB/s]
- 32%|###2 | 13.3M/41.5M [00:10<00:12, 2.41MB/s]
- 33%|###3 | 13.9M/41.5M [00:10<00:10, 2.82MB/s]
- 35%|###4 | 14.5M/41.5M [00:10<00:07, 3.57MB/s]
- 36%|###5 | 14.9M/41.5M [00:10<00:09, 3.08MB/s]
- 37%|###6 | 15.2M/41.5M [00:10<00:10, 2.59MB/s]
- 38%|###8 | 15.9M/41.5M [00:10<00:07, 3.47MB/s]
- 39%|###9 | 16.3M/41.5M [00:11<00:07, 3.42MB/s]
- 40%|#### | 16.7M/41.5M [00:11<00:08, 3.10MB/s]
- 42%|####2 | 17.4M/41.5M [00:11<00:06, 4.05MB/s]
- 44%|####3 | 18.2M/41.5M [00:11<00:04, 4.94MB/s]
- 45%|####5 | 18.7M/41.5M [00:11<00:05, 4.18MB/s]
- 46%|####6 | 19.2M/41.5M [00:11<00:06, 3.40MB/s]
- 48%|####8 | 20.0M/41.5M [00:11<00:05, 4.13MB/s]
- 50%|##### | 20.9M/41.5M [00:12<00:04, 5.04MB/s]
- 52%|#####1 | 21.4M/41.5M [00:12<00:04, 4.35MB/s]
- 53%|#####2 | 21.9M/41.5M [00:12<00:04, 4.44MB/s]
- 55%|#####5 | 22.9M/41.5M [00:12<00:03, 5.67MB/s]
- 57%|#####6 | 23.5M/41.5M [00:12<00:04, 4.65MB/s]
- 58%|#####7 | 24.0M/41.5M [00:12<00:04, 4.55MB/s]
- 60%|###### | 25.1M/41.5M [00:12<00:02, 5.87MB/s]
- 62%|######1 | 25.7M/41.5M [00:13<00:03, 4.84MB/s]
- 63%|######3 | 26.3M/41.5M [00:13<00:03, 5.07MB/s]
- 66%|######6 | 27.5M/41.5M [00:13<00:02, 6.64MB/s]
- 68%|######7 | 28.2M/41.5M [00:13<00:02, 5.93MB/s]
- 69%|######9 | 28.8M/41.5M [00:13<00:02, 5.74MB/s]
- 72%|#######1 | 29.8M/41.5M [00:13<00:01, 6.84MB/s]
- 74%|#######3 | 30.5M/41.5M [00:13<00:02, 5.38MB/s]
- 76%|#######5 | 31.5M/41.5M [00:14<00:01, 5.94MB/s]
- 79%|#######9 | 32.9M/41.5M [00:14<00:01, 7.82MB/s]
- 81%|########1 | 33.8M/41.5M [00:14<00:01, 6.90MB/s]
- 83%|########3 | 34.5M/41.5M [00:14<00:01, 6.01MB/s]
- 87%|########6 | 35.9M/41.5M [00:14<00:00, 7.10MB/s]
- 90%|########9 | 37.3M/41.5M [00:14<00:00, 8.58MB/s]
- 92%|#########2| 38.2M/41.5M [00:14<00:00, 7.13MB/s]
- 94%|#########3| 39.0M/41.5M [00:15<00:00, 5.97MB/s]
- 97%|#########7| 40.3M/41.5M [00:15<00:00, 7.34MB/s]
-100%|##########| 41.5M/41.5M [00:15<00:00, 2.82MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:42, 94.0kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:52, 149kB/s]
+ 0%| | 96.0k/41.5M [00:00<03:27, 209kB/s]
+ 0%| | 208k/41.5M [00:00<01:52, 385kB/s]
+ 1%|1 | 432k/41.5M [00:00<00:59, 718kB/s]
+ 2%|2 | 872k/41.5M [00:01<00:31, 1.35MB/s]
+ 4%|4 | 1.72M/41.5M [00:01<00:16, 2.60MB/s]
+ 8%|7 | 3.26M/41.5M [00:01<00:08, 4.70MB/s]
+ 12%|#1 | 4.80M/41.5M [00:01<00:06, 6.11MB/s]
+ 15%|#5 | 6.34M/41.5M [00:01<00:05, 7.07MB/s]
+ 19%|#8 | 7.88M/41.5M [00:01<00:04, 7.72MB/s]
+ 23%|##2 | 9.41M/41.5M [00:02<00:04, 8.17MB/s]
+ 26%|##6 | 10.9M/41.5M [00:02<00:03, 8.47MB/s]
+ 30%|### | 12.5M/41.5M [00:02<00:03, 8.69MB/s]
+ 34%|###3 | 14.0M/41.5M [00:02<00:03, 8.82MB/s]
+ 37%|###7 | 15.5M/41.5M [00:02<00:03, 8.93MB/s]
+ 41%|####1 | 17.1M/41.5M [00:02<00:02, 9.02MB/s]
+ 45%|####4 | 18.6M/41.5M [00:03<00:02, 9.06MB/s]
+ 49%|####8 | 20.2M/41.5M [00:03<00:02, 9.10MB/s]
+ 52%|#####2 | 21.7M/41.5M [00:03<00:02, 9.09MB/s]
+ 56%|#####5 | 23.2M/41.5M [00:03<00:02, 9.12MB/s]
+ 60%|#####9 | 24.8M/41.5M [00:03<00:01, 9.15MB/s]
+ 63%|######3 | 26.3M/41.5M [00:04<00:01, 9.16MB/s]
+ 66%|######5 | 27.2M/41.5M [00:04<00:01, 7.56MB/s]
+ 69%|######9 | 28.8M/41.5M [00:04<00:01, 8.03MB/s]
+ 71%|#######1 | 29.6M/41.5M [00:04<00:01, 7.69MB/s]
+ 75%|#######5 | 31.2M/41.5M [00:04<00:01, 8.16MB/s]
+ 79%|#######8 | 32.7M/41.5M [00:04<00:01, 8.47MB/s]
+ 83%|########2 | 34.2M/41.5M [00:05<00:00, 8.70MB/s]
+ 86%|########6 | 35.8M/41.5M [00:05<00:00, 8.84MB/s]
+ 90%|########9 | 37.3M/41.5M [00:05<00:00, 8.95MB/s]
+ 94%|#########3| 38.9M/41.5M [00:05<00:00, 9.00MB/s]
+ 97%|#########7| 40.4M/41.5M [00:05<00:00, 9.06MB/s]
+ 99%|#########9| 41.3M/41.5M [00:06<00:00, 7.35MB/s]
+100%|##########| 41.5M/41.5M [00:06<00:00, 7.24MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_paddle.html b/docs/how_to/compile_models/from_paddle.html
index 32f73161d..16736c7cb 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -488,7 +488,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 9.376 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 5.825 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-paddle-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/16269b77359771348d507395692524cf/from_paddle.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_paddle.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/from_pytorch.html b/docs/how_to/compile_models/from_pytorch.html
index 26c1b534a..3bda207b8 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -409,8 +409,10 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 46%|####5 | 20.4M/44.7M [00:00<00:00, 214MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 244MB/s]
+ 9%|8 | 3.95M/44.7M [00:00<00:01, 41.4MB/s]
+ 27%|##7 | 12.2M/44.7M [00:00<00:00, 68.1MB/s]
+ 62%|######2 | 27.8M/44.7M [00:00<00:00, 111MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 122MB/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 2dfaaa2ef..f6f3dbd20 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -631,7 +631,7 @@ 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 4.892 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 1.946 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-compile-models-from-tensorflow-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7f1d3d1b878694c201c614c807cdebc8/from_tensorflow.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">from_tensorflow.py</span></code></a></p>
diff --git a/docs/how_to/compile_models/sg_execution_times.html b/docs/how_to/compile_models/sg_execution_times.html
index b85f2a865..81ae3421b 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:44.307</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>05:22.379</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,43 +331,43 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="from_paddle.html#sphx-glr-how-to-compile-models-from-paddle-py"><span class="std std-ref">Compile PaddlePaddle Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_paddle.py</span></code>)</p></td>
-<td><p>01:09.376</p></td>
+<td><p>01:05.825</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_tensorflow.html#sphx-glr-how-to-compile-models-from-tensorflow-py"><span class="std std-ref">Compile Tensorflow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tensorflow.py</span></code>)</p></td>
-<td><p>01:04.892</p></td>
+<td><p>01:01.946</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_darknet.html#sphx-glr-how-to-compile-models-from-darknet-py"><span class="std std-ref">Compile YOLO-V2 and YOLO-V3 in DarkNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_darknet.py</span></code>)</p></td>
-<td><p>00:59.982</p></td>
+<td><p>00:57.694</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_oneflow.html#sphx-glr-how-to-compile-models-from-oneflow-py"><span class="std std-ref">Compile OneFlow Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_oneflow.py</span></code>)</p></td>
-<td><p>00:44.635</p></td>
+<td><p>00:31.859</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_tflite.html#sphx-glr-how-to-compile-models-from-tflite-py"><span class="std std-ref">Compile TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_tflite.py</span></code>)</p></td>
-<td><p>00:24.085</p></td>
+<td><p>00:23.901</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_mxnet.html#sphx-glr-how-to-compile-models-from-mxnet-py"><span class="std std-ref">Compile MXNet Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_mxnet.py</span></code>)</p></td>
-<td><p>00:22.972</p></td>
+<td><p>00:23.763</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_coreml.html#sphx-glr-how-to-compile-models-from-coreml-py"><span class="std std-ref">Compile CoreML Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_coreml.py</span></code>)</p></td>
-<td><p>00:22.015</p></td>
+<td><p>00:21.567</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:19.534</p></td>
+<td><p>00:19.344</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="from_keras.html#sphx-glr-how-to-compile-models-from-keras-py"><span class="std std-ref">Compile Keras Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_keras.py</span></code>)</p></td>
-<td><p>00:14.256</p></td>
+<td><p>00:14.126</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="from_onnx.html#sphx-glr-how-to-compile-models-from-onnx-py"><span class="std std-ref">Compile ONNX Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_onnx.py</span></code>)</p></td>
-<td><p>00:02.561</p></td>
+<td><p>00:02.355</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/deploy_models/deploy_model_on_android.html b/docs/how_to/deploy_models/deploy_model_on_android.html
index 60d90974d..2bceed688 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -648,7 +648,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 16.3085 16.2316 16.6068 16.1153 0.1688
+ 15.9979 15.9347 16.5312 15.7462 0.2189
</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 54f54aa55..f4dd8492d 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -431,15 +431,17 @@ 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 | 4.85M/170M [00:00<00:03, 50.8MB/s]
- 6%|5 | 9.91M/170M [00:00<00:03, 52.1MB/s]
- 20%|## | 34.1M/170M [00:00<00:00, 144MB/s]
- 35%|###4 | 59.3M/170M [00:00<00:00, 192MB/s]
- 50%|####9 | 84.3M/170M [00:00<00:00, 217MB/s]
- 64%|######4 | 109M/170M [00:00<00:00, 232MB/s]
- 79%|#######8 | 134M/170M [00:00<00:00, 241MB/s]
- 94%|#########3| 159M/170M [00:00<00:00, 248MB/s]
-100%|##########| 170M/170M [00:00<00:00, 211MB/s]
+ 1%| | 1.27M/170M [00:00<00:13, 13.1MB/s]
+ 2%|2 | 3.42M/170M [00:00<00:09, 18.4MB/s]
+ 5%|4 | 8.40M/170M [00:00<00:05, 33.6MB/s]
+ 11%|#1 | 19.1M/170M [00:00<00:02, 64.2MB/s]
+ 24%|##3 | 40.3M/170M [00:00<00:01, 121MB/s]
+ 37%|###7 | 63.6M/170M [00:00<00:00, 163MB/s]
+ 51%|#####1 | 87.3M/170M [00:00<00:00, 191MB/s]
+ 65%|######5 | 111M/170M [00:00<00:00, 208MB/s]
+ 79%|#######9 | 135M/170M [00:00<00:00, 221MB/s]
+ 93%|#########3| 158M/170M [00:01<00:00, 229MB/s]
+100%|##########| 170M/170M [00:01<00:00, 169MB/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').
@@ -534,7 +536,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 59.141 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 54.429 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-object-detection-pytorch-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7795da4b258c8feff986668b95ef57ad/deploy_object_detection_pytorch.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_object_detection_pytorch.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized.html b/docs/how_to/deploy_models/deploy_prequantized.html
index a49432f51..338900983 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -472,10 +472,11 @@ 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]
- 20%|#9 | 2.68M/13.6M [00:00<00:00, 27.6MB/s]
- 60%|###### | 8.17M/13.6M [00:00<00:00, 45.1MB/s]
- 92%|#########2| 12.5M/13.6M [00:00<00:00, 34.1MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 34.3MB/s]
+ 6%|6 | 880k/13.6M [00:00<00:01, 8.96MB/s]
+ 18%|#8 | 2.48M/13.6M [00:00<00:00, 13.6MB/s]
+ 40%|#### | 5.43M/13.6M [00:00<00:00, 21.5MB/s]
+ 80%|#######9 | 10.8M/13.6M [00:00<00:00, 35.2MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 32.6MB/s]
</pre></div>
</div>
</div>
@@ -564,7 +565,7 @@ output values are identical out of 1000 outputs from mobilenet v2.</p>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 90.3879 90.3525 90.8283 90.2179 0.1102
+ 90.4646 90.2163 100.8701 90.0853 1.3153
</pre></div>
</div>
<div class="admonition note">
@@ -603,7 +604,7 @@ 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 8.636 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.399 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/fb8217c13f4351224c6cf3aacf1a87fc/deploy_prequantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_prequantized_tflite.html b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
index 1875f342e..c06f90463 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -565,7 +565,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 120.2575 120.1504 122.0605 119.3781 0.4370
+ 119.3751 119.3254 120.2596 118.6613 0.3022
</pre></div>
</div>
<div class="admonition note">
@@ -593,7 +593,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 53.074 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 51.697 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-prequantized-tflite-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/56691c7a27d45da61d112276334640d3/deploy_prequantized_tflite.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_prequantized_tflite.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_quantized.html b/docs/how_to/deploy_models/deploy_quantized.html
index 7b3a13cec..aed264455 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -504,7 +504,7 @@ 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 13.619 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 29.035 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-quantized-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/7810ecf51bfc05f7d5e8a400ac3e815d/deploy_quantized.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_quantized.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
index 60aa32572..5ffeca38f 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -436,22 +436,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|4 | 6432/132723 [00:00<00:01, 64313.77KB/s]
- 11%|#1 | 14834/132723 [00:00<00:01, 75900.25KB/s]
- 18%|#7 | 23314/132723 [00:00<00:01, 79958.82KB/s]
- 24%|##3 | 31741/132723 [00:00<00:01, 81656.04KB/s]
- 30%|### | 40158/132723 [00:00<00:01, 82558.86KB/s]
- 37%|###6 | 48494/132723 [00:00<00:01, 82828.36KB/s]
- 43%|####2 | 56902/132723 [00:00<00:00, 83235.86KB/s]
- 49%|####9 | 65345/132723 [00:00<00:00, 83612.84KB/s]
- 56%|#####5 | 73794/132723 [00:00<00:00, 83885.12KB/s]
- 62%|######1 | 82264/132723 [00:01<00:00, 84135.28KB/s]
- 68%|######8 | 90687/132723 [00:01<00:00, 84156.61KB/s]
- 75%|#######4 | 99128/132723 [00:01<00:00, 84231.03KB/s]
- 81%|########1 | 107593/132723 [00:01<00:00, 84354.43KB/s]
- 87%|########7 | 116058/132723 [00:01<00:00, 84441.04KB/s]
- 94%|#########3| 124571/132723 [00:01<00:00, 84638.51KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 83127.04KB/s]
+ 5%|4 | 6010/132723 [00:00<00:02, 60095.90KB/s]
+ 11%|# | 14441/132723 [00:00<00:01, 74337.36KB/s]
+ 17%|#7 | 22880/132723 [00:00<00:01, 78925.54KB/s]
+ 24%|##3 | 31323/132723 [00:00<00:01, 81095.09KB/s]
+ 30%|### | 39842/132723 [00:00<00:01, 82569.00KB/s]
+ 36%|###6 | 48277/132723 [00:00<00:01, 83171.91KB/s]
+ 43%|####2 | 56678/132723 [00:00<00:00, 83443.31KB/s]
+ 49%|####9 | 65163/132723 [00:00<00:00, 83888.20KB/s]
+ 55%|#####5 | 73608/132723 [00:00<00:00, 84060.02KB/s]
+ 62%|######1 | 82087/132723 [00:01<00:00, 84283.34KB/s]
+ 68%|######8 | 90554/132723 [00:01<00:00, 84400.22KB/s]
+ 75%|#######4 | 99024/132723 [00:01<00:00, 84484.57KB/s]
+ 81%|######## | 107473/132723 [00:01<00:00, 84326.68KB/s]
+ 87%|########7 | 115906/132723 [00:01<00:00, 84308.19KB/s]
+ 94%|#########3| 124337/132723 [00:01<00:00, 84249.67KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 82855.34KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -494,7 +494,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 21.941 seconds)</p>
+<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 18.036 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-deploy-models-deploy-ssd-gluoncv-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/cccb17d28e5e8b2e94ea8cd5ec59f6ed/deploy_ssd_gluoncv.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">deploy_ssd_gluoncv.py</span></code></a></p>
diff --git a/docs/how_to/deploy_models/sg_execution_times.html b/docs/how_to/deploy_models/sg_execution_times.html
index 92feccc90..e295e5e63 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:28.651</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:31.098</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -331,31 +331,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:59.141</p></td>
+<td><p>02:54.429</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_ssd_gluoncv.html#sphx-glr-how-to-deploy-models-deploy-ssd-gluoncv-py"><span class="std std-ref">Deploy Single Shot Multibox Detector(SSD) model</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_ssd_gluoncv.py</span></code>)</p></td>
-<td><p>02:21.941</p></td>
+<td><p>02:18.036</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:53.074</p></td>
+<td><p>01:51.697</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_quantized.html#sphx-glr-how-to-deploy-models-deploy-quantized-py"><span class="std std-ref">Deploy a Quantized Model on Cuda</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_quantized.py</span></code>)</p></td>
-<td><p>01:13.619</p></td>
+<td><p>01:29.035</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized.html#sphx-glr-how-to-deploy-models-deploy-prequantized-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized.py</span></code>)</p></td>
-<td><p>01:08.636</p></td>
+<td><p>01:07.399</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_model_on_android.html#sphx-glr-how-to-deploy-models-deploy-model-on-android-py"><span class="std std-ref">Deploy the Pretrained Model on Android</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_android.py</span></code>)</p></td>
-<td><p>00:29.819</p></td>
+<td><p>00:28.619</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_model_on_rasp.html#sphx-glr-how-to-deploy-models-deploy-model-on-rasp-py"><span class="std std-ref">Deploy the Pretrained Model on Raspberry Pi</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_model_on_rasp.py</span></code>)</p></td>
-<td><p>00:22.415</p></td>
+<td><p>00:21.878</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_sparse.html#sphx-glr-how-to-deploy-models-deploy-sparse-py"><span class="std std-ref">Deploy a Hugging Face Pruned Model on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_sparse.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/bring_your_own_datatypes.html b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
index 576d1df52..3940b625a 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -604,7 +604,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipf6306733-7f7c-47e4-8ebe-430ad30112c3 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.zip4b5eceb2-88b7-4508-ac97-14ab3565b274 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 c9192e8c7..70859cc05 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:40.382</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:39.774</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="bring_your_own_datatypes.html#sphx-glr-how-to-extend-tvm-bring-your-own-datatypes-py"><span class="std std-ref">Bring Your Own Datatypes to TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">bring_your_own_datatypes.py</span></code>)</p></td>
-<td><p>00:37.207</p></td>
+<td><p>00:36.589</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="use_pass_instrument.html#sphx-glr-how-to-extend-tvm-use-pass-instrument-py"><span class="std std-ref">How to Use TVM Pass Instrument</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_instrument.py</span></code>)</p></td>
-<td><p>00:02.242</p></td>
+<td><p>00:02.257</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="use_pass_infra.html#sphx-glr-how-to-extend-tvm-use-pass-infra-py"><span class="std std-ref">How to Use TVM Pass Infra</span></a> (<code class="docutils literal notranslate"><span class="pre">use_pass_infra.py</span></code>)</p></td>
-<td><p>00:00.926</p></td>
+<td><p>00:00.922</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="low_level_custom_pass.html#sphx-glr-how-to-extend-tvm-low-level-custom-pass-py"><span class="std std-ref">Writing a Customized Pass</span></a> (<code class="docutils literal notranslate"><span class="pre">low_level_custom_pass.py</span></code>)</p></td>
diff --git a/docs/how_to/extend_tvm/use_pass_instrument.html b/docs/how_to/extend_tvm/use_pass_instrument.html
index 9005f5ab4..7fc104db6 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -507,10 +507,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6528us [6528us] (45.88%; 45.88%)
-FoldScaleAxis: 7699us [6us] (54.12%; 54.12%)
- FoldConstant: 7693us [1564us] (54.08%; 99.93%)
- InferType: 6129us [6129us] (43.08%; 79.67%)
+InferType: 7271us [7271us] (46.43%; 46.43%)
+FoldScaleAxis: 8388us [6us] (53.57%; 53.57%)
+ FoldConstant: 8382us [1669us] (53.53%; 99.93%)
+ InferType: 6713us [6713us] (42.87%; 80.09%)
</pre></div>
</div>
</div>
@@ -532,10 +532,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6179us [6179us] (44.70%; 44.70%)
-FoldScaleAxis: 7646us [6us] (55.30%; 55.30%)
- FoldConstant: 7640us [1575us] (55.26%; 99.93%)
- InferType: 6065us [6065us] (43.87%; 79.38%)
+InferType: 6723us [6723us] (44.81%; 44.81%)
+FoldScaleAxis: 8281us [5us] (55.19%; 55.19%)
+ FoldConstant: 8276us [1702us] (55.16%; 99.94%)
+ InferType: 6574us [6574us] (43.81%; 79.43%)
</pre></div>
</div>
<p>Register empty list to clear existing instruments.</p>
diff --git a/docs/how_to/optimize_operators/opt_conv_cuda.html b/docs/how_to/optimize_operators/opt_conv_cuda.html
index ca4200a93..76d59ebc2 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -556,7 +556,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.199867 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.142719 ms
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-optimize-operators-opt-conv-cuda-py">
diff --git a/docs/how_to/optimize_operators/opt_conv_tensorcore.html b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
index 44c68471f..c7e0bb311 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -898,7 +898,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.875362 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 6.906179 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 b8e3ae24f..d626e07d0 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -453,8 +453,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019028
-Baseline: 3.404544
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019387
+Baseline: 3.341706
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -514,7 +514,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.323016
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.307661
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -581,7 +581,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.352187
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.349376
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -642,7 +642,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.119966
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118716
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -725,7 +725,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110545
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110635
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -811,7 +811,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111549
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111683
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -901,7 +901,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.146698
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145276
</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 3e04a6ff9..b9feb5a8b 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:35.118</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.598</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.802</p></td>
+<td><p>00:32.358</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="opt_conv_tensorcore.html#sphx-glr-how-to-optimize-operators-opt-conv-tensorcore-py"><span class="std std-ref">How to optimize convolution using TensorCores</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_tensorcore.py</span></code>)</p></td>
-<td><p>00:01.255</p></td>
+<td><p>00:01.233</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_conv_cuda.html#sphx-glr-how-to-optimize-operators-opt-conv-cuda-py"><span class="std std-ref">How to optimize convolution on GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_conv_cuda.py</span></code>)</p></td>
-<td><p>00:01.060</p></td>
+<td><p>00:01.007</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
index c277d6fd9..6d63ddf12 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:14.820</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:22.741</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -331,27 +331,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>02:35.281</p></td>
+<td><p>02:36.299</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-x86-py"><span class="std std-ref">Auto-scheduling a Neural Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_x86.py</span></code>)</p></td>
-<td><p>01:21.177</p></td>
+<td><p>01:19.969</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-cuda-py"><span class="std std-ref">Auto-scheduling a Neural Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_cuda.py</span></code>)</p></td>
-<td><p>00:43.360</p></td>
+<td><p>00:42.898</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:17.508</p></td>
+<td><p>00:26.436</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_network_mali.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-mali-py"><span class="std std-ref">Auto-scheduling a Neural Network for mali GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_mali.py</span></code>)</p></td>
-<td><p>00:08.883</p></td>
+<td><p>00:08.588</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_network_arm.html#sphx-glr-how-to-tune-with-autoscheduler-tune-network-arm-py"><span class="std std-ref">Auto-scheduling a Neural Network for ARM CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_network_arm.py</span></code>)</p></td>
-<td><p>00:08.611</p></td>
+<td><p>00:08.551</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_conv2d_layer_cuda.html
index d97e1ef02..b7adbf448 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
@@ -486,107 +486,939 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 16;
- allocate(conv2d_nchw: Pointer(local float32), float32, [8]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [2016]), storage_scope = shared;
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 112;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [672]), storage_scope = shared;
allocate(kernel.shared: Pointer(shared float32), float32, [3072]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [8], [], scope="local", align=32)[0] = 0f32
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [7], [], scope="local", align=16)[0] = 0f32
conv2d_nchw_1[1] = 0f32
conv2d_nchw_1[2] = 0f32
conv2d_nchw_1[3] = 0f32
conv2d_nchw_1[4] = 0f32
conv2d_nchw_1[5] = 0f32
conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[7] = 0f32
for (rc.outer.outer: int32, 0, 16) {
for (ry.outer.outer: int32, 0, 3) {
- let cse_var_4: int32 = (rc.outer.outer*1568)
- let cse_var_3: int32 = (ry.outer.outer*7)
- let cse_var_2: int32 = (rc.outer.outer*288)
+ let cse_var_3: int32 = (rc.outer.outer*1568)
+ let cse_var_2: int32 = (ry.outer.outer*7)
let cse_var_1: int32 = (ry.outer.outer*3)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [2016], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) - 8)], 0f [...]
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 196)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 196), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 196), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 392)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 392), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 5), 9))) && (floormod((threadIdx.x_1 + 5), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 392), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 5), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 588)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 588), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 3), 9))) && (floormod((threadIdx.x_1 + 3), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 588), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 3), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 784)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 784), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 1), 9))) && (floormod((threadIdx.x_1 + 1), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 784), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 1), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 980)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 980), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 8), 9))) && (floormod((threadIdx.x_1 + 8), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 980), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 8), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1176)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1176), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 6), 9))) && (floormod((threadIdx.x_1 + 6), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1176), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 6), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1372)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1372), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 4), 9))) && (floormod((threadIdx.x_1 + 4), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1372), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 4), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1568)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1568), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 2), 9))) && (floormod((threadIdx.x_1 + 2), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1568), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 2), 9)) - 8)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- pad_temp.shared_1[(threadIdx.x_1 + 1764)] = @tir.if_then_else(((((1 <= (floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer)) && ((floordiv(floormod(threadIdx.x_1, 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod(threadIdx.x_1, 9))) && (floormod(threadIdx.x_1, 9) < 8)), data[((((cse_var_4 + (floordiv(threadIdx.x_1, 9)*7)) + cse_var_3) + floormod(threadIdx.x_1, 9)) + 1364)], 0f32, dtype=float32)
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_1 < 56), dtype=bool) {
- pad_temp.shared_1[(threadIdx.x_1 + 1960)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1 + 1960), 63), 9) + ry.outer.outer) < 8)) && (1 <= floormod((threadIdx.x_1 + 7), 9))) && (floormod((threadIdx.x_1 + 7), 9) < 8)), data[((((cse_var_4 + (floordiv((threadIdx.x_1 + 1960), 9)*7)) + cse_var_3) + floormod((threadIdx.x_1 + 7), 9)) - 8)], 0f32, dtype=float32)
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [672], [], scope="shared")[(threadIdx.x_1*8)] = @tir.if_then_else(((((1 <= (floordiv(floormod((threadIdx.x_1*8), 21), 3) + ry.outer.outer)) && ((floordiv(floormod((threadIdx.x_1*8), 21), 3) + ry.outer.outer) < 8)) && (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_3 + (floor [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 1)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 1), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 1), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 1), 3)*7)) + cse [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 2)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 2), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 2), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 2), 3)*7)) + cse [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 3)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 1), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(b [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 4)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 4), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 4), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 4), 3)*7)) + cse [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 5)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 5), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 5), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 5), 3)*7)) + cse [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 6)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod(b [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 7)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 7), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 7), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 7), 3)*7)) + cse [...]
}
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[((((((blockIdx.x*147456) + (floordiv(threadIdx.x_2, 96)*4608)) + cse_var_2) + (floordiv(floormod(threadIdx.x_2, 96), 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 196)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 49), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 4), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 392)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 98), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 8), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 588)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 147), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 4), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 784)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 196), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 16), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 980)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 245), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 20), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1176)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 294), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 8), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1372)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 343), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 28), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 392), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 32), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1764)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 441), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 12), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 1960)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 490), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 40), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2156)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 539), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 44), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2352)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 588), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 16), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2548)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 637), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 52), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- kernel.shared_1[(threadIdx.x_2 + 2744)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 686), 24)*4608)) + cse_var_2) + (floordiv(floormod((threadIdx.x_2 + 56), 96), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 196;
- if @tir.likely((threadIdx.x_2 < 132), dtype=bool) {
- kernel.shared_1[(threadIdx.x_2 + 2940)] = kernel[((((((blockIdx.x*147456) + (floordiv((floordiv(threadIdx.x_2, 4) + 735), 24)*4608)) + cse_var_2) + (floormod((floordiv(threadIdx.x_2, 3) + 20), 32)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 256)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 256), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 256), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 256), 3)*7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 257)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 257), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 257), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 257), 3)*7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 258)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 2), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 259)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 1), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 260)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 260), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 260), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 260), 3)*7 [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 261)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floormod [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 262)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 256), 3) + 2), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + [...]
+ pad_temp.shared_1[((threadIdx.x_1*8) + 263)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 263), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 263), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 263), 3)*7 [...]
}
- for (rc.outer.inner: int32, 0, 2) {
- for (rx.outer.inner: int32, 0, 3) {
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 16) {
- let cse_var_8: int32 = (ff.outer.inner*4)
- let cse_var_7: int32 = (cse_var_8 + 3)
- let cse_var_6: int32 = (cse_var_8 + 2)
- let cse_var_5: int32 = (cse_var_8 + 1)
- {
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[(((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 96)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 192)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((((rc.outer.inner*1008) + (rc.inner*63)) + (floordiv(floormod(threadIdx.x, 49), 7)*9)) + rx.outer.inner) + floormod(threadIdx.x, 7))]*kernel.shared_1[((((((floordiv(threadIdx.x, 49)*768) + (ff.outer.inner*384)) + (rc.outer.inner*48)) + (rc.inner*3)) + rx.outer.inner) + 288)]))
- }
- }
- }
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32 {
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 512)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 512), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 512), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 512), 3) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 513)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 3), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floorm [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 514)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 514), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 514), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 514), 3) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 515)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 1), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 1), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 516)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 4), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 4), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floorm [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 517)] = @tir.if_then_else(((((1 <= (floordiv(floormod(((threadIdx.x_1*8) + 517), 21), 3) + ry.outer.outer)) && ((floordiv(floormod(((threadIdx.x_1*8) + 517), 21), 3) + ry.outer.outer) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 1), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) + 517), 3) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 518)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 2), 7))) && ((ry.outer.outer + floormod((floordiv(((threadIdx.x_1*8) + 512), 3) + 2), 7)) < 8)) && (1 <= (floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod(((threadIdx.x_1*2) + 2), 3)) < 8)), data[(((((cse_var_3 + (floordiv(((threadIdx.x_1*8) [...]
+ }
+ if @tir.likely((threadIdx.x_1 < 20), dtype=bool) {
+ pad_temp.shared_1[((threadIdx.x_1*8) + 519)] = @tir.if_then_else(((((1 <= (ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 5), 7))) && ((ry.outer.outer + floormod((floordiv((threadIdx.x_1*8), 3) + 5), 7)) < 8)) && (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_3 + (floordiv((threadIdx.x_1*8), 3)*7)) + cse_var_2) + floorm [...]
}
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1: Buffer(kernel.shared, float32, [3072], [], scope="shared")[threadIdx.x_2] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 32)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 64)] = kernel[(((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 96)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 160)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 4608)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 192)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 224)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 9216)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 288)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 320)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 352)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 13824)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 416)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 448)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 18432)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 480)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 544)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 23040)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 576)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 608)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 27648)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 672)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 704)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 736)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 32256)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 800)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 832)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 36864)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 864)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 928)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 41472)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 960)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 992)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 46080)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1056)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1088)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1120)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 50688)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1184)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1216)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 55296)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1248)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1312)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 59904)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1344)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1376)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 64512)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1440)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1472)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1504)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 69120)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1568)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1600)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1632)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1696)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 78336)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1728)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1760)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 82944)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1824)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1856)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1888)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 87552)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1952)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 1984)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 92160)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2016)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2080)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 96768)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2112)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2144)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 101376)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2208)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2240)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2272)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 105984)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2336)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2368)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 110592)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2400)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2464)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 115200)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2496)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2528)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 119808)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2592)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2624)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2656)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 124416)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2720)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2752)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 129024)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2784)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2848)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 133632)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2880)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2912)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 138240)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 2976)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv(threadIdx.x_2, 3)*9)) + cse_var_1) + floormod(threadIdx.x_2, 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3008)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 32), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 2), 3)) + 142848)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 32;
+ kernel.shared_1[(threadIdx.x_2 + 3040)] = kernel[((((((floordiv(blockIdx.x, 7)*147456) + (rc.outer.outer*288)) + (floordiv((threadIdx.x_2 + 64), 3)*9)) + cse_var_1) + floormod((threadIdx.x_2 + 1), 3)) + 142848)]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*96)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*96) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*96) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*96) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*96) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*96) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*96) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*96) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*96) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*96) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*96) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*96) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*96) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*96) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*96) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*96) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*96) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*96) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*96) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*96) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*96) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*96) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*96) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*96) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*96) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*96) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*96) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*96) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*96) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*96) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[216]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[219]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[222]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[225]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[228]*kernel.shared_1[((threadIdx.x*96) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[217]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[220]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[223]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[226]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[229]*kernel.shared_1[((threadIdx.x*96) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[218]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[221]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[224]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[227]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[230]*kernel.shared_1[((threadIdx.x*96) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[231]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[234]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[237]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[240]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[243]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[246]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[249]*kernel.shared_1[((threadIdx.x*96) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[232]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[235]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[238]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[241]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[244]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[247]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[250]*kernel.shared_1[((threadIdx.x*96) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[233]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[236]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[239]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[242]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[245]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[248]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[251]*kernel.shared_1[((threadIdx.x*96) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[252]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[255]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[258]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[261]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[264]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[267]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[270]*kernel.shared_1[((threadIdx.x*96) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[253]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[256]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[259]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[262]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[265]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[268]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[271]*kernel.shared_1[((threadIdx.x*96) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[254]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[257]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[260]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[263]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[266]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[269]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[272]*kernel.shared_1[((threadIdx.x*96) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[273]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[276]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[279]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[282]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[285]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[288]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[291]*kernel.shared_1[((threadIdx.x*96) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[274]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[277]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[280]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[283]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[286]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[289]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[292]*kernel.shared_1[((threadIdx.x*96) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[275]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[278]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[281]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[284]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[287]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[290]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[293]*kernel.shared_1[((threadIdx.x*96) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[294]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[297]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[300]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[303]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[306]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[309]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[312]*kernel.shared_1[((threadIdx.x*96) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[295]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[298]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[301]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[304]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[307]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[310]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[313]*kernel.shared_1[((threadIdx.x*96) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[296]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[299]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[302]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[305]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[308]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[311]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[314]*kernel.shared_1[((threadIdx.x*96) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[315]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[318]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[321]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[324]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[327]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[330]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[333]*kernel.shared_1[((threadIdx.x*96) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[316]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[319]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[322]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[325]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[328]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[331]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[334]*kernel.shared_1[((threadIdx.x*96) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[317]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[320]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[323]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[326]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[329]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[332]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[335]*kernel.shared_1[((threadIdx.x*96) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[336]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[339]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[342]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[345]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[348]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[351]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[354]*kernel.shared_1[((threadIdx.x*96) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[337]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[340]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[343]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[346]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[349]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[352]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[355]*kernel.shared_1[((threadIdx.x*96) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[338]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[341]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[344]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[347]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[350]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[353]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[356]*kernel.shared_1[((threadIdx.x*96) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[357]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[360]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[363]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[366]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[369]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[372]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[375]*kernel.shared_1[((threadIdx.x*96) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[358]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[361]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[364]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[367]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[370]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[373]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[376]*kernel.shared_1[((threadIdx.x*96) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[359]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[362]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[365]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[368]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[371]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[374]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[377]*kernel.shared_1[((threadIdx.x*96) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[378]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[381]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[384]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[387]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[390]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[393]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[396]*kernel.shared_1[((threadIdx.x*96) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[379]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[382]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[385]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[388]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[391]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[394]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[397]*kernel.shared_1[((threadIdx.x*96) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[380]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[383]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[386]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[389]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[392]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[395]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[398]*kernel.shared_1[((threadIdx.x*96) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[399]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[402]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[405]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[408]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[411]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[414]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[417]*kernel.shared_1[((threadIdx.x*96) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[400]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[403]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[406]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[409]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[412]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[415]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[418]*kernel.shared_1[((threadIdx.x*96) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[401]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[404]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[407]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[410]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[413]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[416]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[419]*kernel.shared_1[((threadIdx.x*96) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[420]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[423]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[426]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[429]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[432]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[435]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[438]*kernel.shared_1[((threadIdx.x*96) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[421]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[424]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[427]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[430]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[433]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[436]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[439]*kernel.shared_1[((threadIdx.x*96) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[422]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[425]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[428]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[431]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[434]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[437]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[440]*kernel.shared_1[((threadIdx.x*96) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[441]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[444]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[447]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[450]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[453]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[456]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[459]*kernel.shared_1[((threadIdx.x*96) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[442]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[445]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[448]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[451]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[454]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[457]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[460]*kernel.shared_1[((threadIdx.x*96) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[443]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[446]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[449]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[452]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[455]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[458]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[461]*kernel.shared_1[((threadIdx.x*96) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[462]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[465]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[468]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[471]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[474]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[477]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[480]*kernel.shared_1[((threadIdx.x*96) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[463]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[466]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[469]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[472]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[475]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[478]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[481]*kernel.shared_1[((threadIdx.x*96) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[464]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[467]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[470]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[473]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[476]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[479]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[482]*kernel.shared_1[((threadIdx.x*96) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[483]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[486]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[489]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[492]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[495]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[498]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[501]*kernel.shared_1[((threadIdx.x*96) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[484]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[487]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[490]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[493]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[496]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[499]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[502]*kernel.shared_1[((threadIdx.x*96) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[485]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[488]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[491]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[494]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[497]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[500]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[503]*kernel.shared_1[((threadIdx.x*96) + 71)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[504]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[507]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[510]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[513]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[516]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[519]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[522]*kernel.shared_1[((threadIdx.x*96) + 72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[505]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[508]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[511]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[514]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[517]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[520]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[523]*kernel.shared_1[((threadIdx.x*96) + 73)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[506]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[509]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[512]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[515]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[518]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[521]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[524]*kernel.shared_1[((threadIdx.x*96) + 74)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[525]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[528]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[531]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[534]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[537]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[540]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[543]*kernel.shared_1[((threadIdx.x*96) + 75)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[526]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[529]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[532]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[535]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[538]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[541]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[544]*kernel.shared_1[((threadIdx.x*96) + 76)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[527]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[530]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[533]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[536]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[539]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[542]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[545]*kernel.shared_1[((threadIdx.x*96) + 77)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[546]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[549]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[552]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[555]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[558]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[561]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[564]*kernel.shared_1[((threadIdx.x*96) + 78)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[547]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[550]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[553]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[556]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[559]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[562]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[565]*kernel.shared_1[((threadIdx.x*96) + 79)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[548]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[551]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[554]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[557]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[560]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[563]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[566]*kernel.shared_1[((threadIdx.x*96) + 80)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[567]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[570]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[573]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[576]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[579]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[582]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[585]*kernel.shared_1[((threadIdx.x*96) + 81)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[568]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[571]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[574]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[577]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[580]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[583]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[586]*kernel.shared_1[((threadIdx.x*96) + 82)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[569]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[572]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[575]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[578]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[581]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[584]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[587]*kernel.shared_1[((threadIdx.x*96) + 83)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[588]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[591]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[594]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[597]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[600]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[603]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[606]*kernel.shared_1[((threadIdx.x*96) + 84)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[589]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[592]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[595]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[598]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[601]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[604]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[607]*kernel.shared_1[((threadIdx.x*96) + 85)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[590]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[593]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[596]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[599]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[602]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[605]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[608]*kernel.shared_1[((threadIdx.x*96) + 86)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[609]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[612]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[615]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[618]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[621]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[624]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[627]*kernel.shared_1[((threadIdx.x*96) + 87)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[610]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[613]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[616]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[619]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[622]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[625]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[628]*kernel.shared_1[((threadIdx.x*96) + 88)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[611]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[614]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[617]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[620]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[623]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[626]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[629]*kernel.shared_1[((threadIdx.x*96) + 89)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[630]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[633]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[636]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[639]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[642]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[645]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[648]*kernel.shared_1[((threadIdx.x*96) + 90)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[631]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[634]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[637]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[640]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[643]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[646]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[649]*kernel.shared_1[((threadIdx.x*96) + 91)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[632]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[635]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[638]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[641]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[644]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[647]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[650]*kernel.shared_1[((threadIdx.x*96) + 92)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[651]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[654]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[657]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[660]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[663]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[666]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[669]*kernel.shared_1[((threadIdx.x*96) + 93)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[652]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[655]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[658]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[661]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[664]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[667]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[670]*kernel.shared_1[((threadIdx.x*96) + 94)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[653]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[656]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[659]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[662]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[665]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[668]*kernel.shared_1[((threadIdx.x*96) + 95)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[671]*kernel.shared_1[((threadIdx.x*96) + 95)]))
}
}
}
- for (i1.inner: int32, 0, 8) {
- compute[((((blockIdx.x*1568) + (floordiv(threadIdx.x, 49)*392)) + (i1.inner*49)) + floormod(threadIdx.x, 49))] = max((conv2d_nchw_1[i1.inner] + bias[(((blockIdx.x*32) + (floordiv(threadIdx.x, 49)*8)) + 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)
}
}
}
@@ -623,7 +1455,7 @@ cooperative fetching, unrolling and operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.310 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.404 ms
</pre></div>
</div>
</div>
@@ -652,36 +1484,36 @@ 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=4)
-conv2d_nchw_ff_o_o_i, conv2d_nchw_ff_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_i, factor=2)
-conv2d_nchw_ff_o_o_o_i, conv2d_nchw_ff_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_i, factor=4)
+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=32)
conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
-conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
+conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=7)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=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=16)
conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=2)
conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
-conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=8)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=4)
+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=32)
compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=1)
-compute_i2_o_i, compute_i2_i = s[compute].split(compute_i2, factor=1)
-compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=7)
+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)
@@ -701,14 +1533,14 @@ s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=196)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[kernel_shared].bind(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[pad_temp_shared].fuse(pad_temp_shared_ax0, pad_temp_shared_ax1, pad_temp_shared_ax2, pad_temp_shared_ax3)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
+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=8)
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=196)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=32)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
-s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 16)
+s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 1024)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
CUDA source code:
@@ -726,9 +1558,9 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(196) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[8];
- __shared__ float pad_temp_shared[2016];
+extern "C" __global__ void __launch_bounds__(32) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[672];
__shared__ float kernel_shared[3072];
conv2d_nchw[0] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
@@ -737,58 +1569,822 @@ extern "C" __global__ void __launch_bounds__(196) default_function_ker
conv2d_nchw[4] = 0.000000e+00f;
conv2d_nchw[5] = 0.000000e+00f;
conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
for (int rc_outer_outer = 0; rc_outer_outer < 16; ++rc_outer_outer) {
for (int ry_outer_outer = 0; ry_outer_outer < 3; ++ry_outer_outer) {
__syncthreads();
- pad_temp_shared[((int)threadIdx.x)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 196)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 196) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 392)] = (((((1 <= ((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 14) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 5) % 9))) && (((((int)threadIdx.x) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 392) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 588)] = (((((1 <= ((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 21) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 3) % 9))) && (((((int)threadIdx.x) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 588) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 784)] = (((((1 <= ((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 28) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 1) % 9))) && (((((int)threadIdx.x) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 784) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 980)] = (((((1 <= ((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 35) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 8) % 9))) && (((((int)threadIdx.x) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 980) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1176)] = (((((1 <= ((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 42) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 6) % 9))) && (((((int)threadIdx.x) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1176) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1372)] = (((((1 <= ((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 49) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 4) % 9))) && (((((int)threadIdx.x) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1372) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1568)] = (((((1 <= ((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 56) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 2) % 9))) && (((((int)threadIdx.x) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1568) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[(((int)threadIdx.x) + 1764)] = (((((1 <= (((((int)threadIdx.x) % 63) / 9) + ry_outer_outer)) && ((((((int)threadIdx.x) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= (((int)threadIdx.x) % 9))) && ((((int)threadIdx.x) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + ((((int)threadIdx.x) / 9) * 7)) + (ry_outer_outer * 7)) + (((int)threadIdx.x) % 9)) + 1364)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 56) {
- pad_temp_shared[(((int)threadIdx.x) + 1960)] = (((((1 <= ((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer)) && (((((((int)threadIdx.x) + 7) % 63) / 9) + ry_outer_outer) < 8)) && (1 <= ((((int)threadIdx.x) + 7) % 9))) && (((((int)threadIdx.x) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 1568) + (((((int)threadIdx.x) + 1960) / 9) * 7)) + (ry_outer_outer * 7)) + ((((int)threadIdx.x) + 7) % 9)) - 8)] : 0.000000e+00f);
+ pad_temp_shared[(((int)threadIdx.x) * 8)] = (((((1 <= ((((((int)threadIdx.x) * 8) % 21) / 3) + ry_outer_outer)) && (((((((int)threadIdx.x) * 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockIdx.x) % 7)) + ((( [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 1)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 1) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 1) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 1) / 3) * 7)) + (ry_outer_outer * [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 2)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 2) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 2) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 2) / 3) * 7)) + (ry_outer_outer * [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 3)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 1) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockId [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 4)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 4) / 3) * 7)) + (ry_outer_outer * [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 5)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 5) / 3) * 7)) + (ry_outer_outer * [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 6)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blockId [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 7)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 7) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 7) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 7) / 3) * 7)) + (ry_outer_outer * [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 256)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 4) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + (ry_outer_oute [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 257)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 5) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 257) / 3) * 7)) + (ry_outer_oute [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 258)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)block [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 259)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 260)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 260) / 3) * 7)) + (ry_outer_oute [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 261)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)block [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 262)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 256) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 256) / 3) * 7)) + [...]
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 263)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 11) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 11) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 263) / 3) * 7)) + (ry_outer_ou [...]
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 512)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 8) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) + (ry_outer_ou [...]
}
- kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) * 147456) + ((((int)threadIdx.x) / 96) * 4608)) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 196)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 196) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 4) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 392)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 392) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 8) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 588)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 588) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 4) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 784)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 784) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 16) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 980)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 980) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 20) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1176)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1176) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 8) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1372)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1372) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 28) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1568) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 32) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1764)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1764) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 12) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 1960)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 1960) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 40) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2156)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2156) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 44) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2352)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2352) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 16) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2548)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2548) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 52) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
- kernel_shared[(((int)threadIdx.x) + 2744)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2744) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) + 56) % 96) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
- if (((int)threadIdx.x) < 132) {
- kernel_shared[(((int)threadIdx.x) + 2940)] = kernel[((((((((int)blockIdx.x) * 147456) + (((((int)threadIdx.x) + 2940) / 96) * 4608)) + (rc_outer_outer * 288)) + ((((((int)threadIdx.x) / 3) + 20) & 31) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 513)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 3) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blo [...]
}
- __syncthreads();
- for (int rc_outer_inner = 0; rc_outer_inner < 2; ++rc_outer_inner) {
- for (int rx_outer_inner = 0; rx_outer_inner < 3; ++rx_outer_inner) {
- for (int ff_outer_inner = 0; ff_outer_inner < 2; ++ff_outer_inner) {
- for (int rc_inner = 0; rc_inner < 16; ++rc_inner) {
- conv2d_nchw[(ff_outer_inner * 4)] = (conv2d_nchw[(ff_outer_inner * 4)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner)]));
- conv2d_nchw[((ff_outer_inner * 4) + 1)] = (conv2d_nchw[((ff_outer_inner * 4) + 1)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 96)]));
- conv2d_nchw[((ff_outer_inner * 4) + 2)] = (conv2d_nchw[((ff_outer_inner * 4) + 2)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 192)]));
- conv2d_nchw[((ff_outer_inner * 4) + 3)] = (conv2d_nchw[((ff_outer_inner * 4) + 3)] + (pad_temp_shared[(((((rc_outer_inner * 1008) + (rc_inner * 63)) + (((((int)threadIdx.x) % 49) / 7) * 9)) + rx_outer_inner) + (((int)threadIdx.x) % 7))] * kernel_shared[(((((((((int)threadIdx.x) / 49) * 768) + (ff_outer_inner * 384)) + (rc_outer_inner * 48)) + (rc_inner * 3)) + rx_outer_inner) + 288)]));
- }
- }
- }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 514)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 10) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 10) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 514) / 3) * 7)) + (ry_outer_ [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 515)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 1) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 1) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 516)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 4) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 4) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blo [...]
}
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 517)] = (((((1 <= (((((((int)threadIdx.x) * 8) + 13) % 21) / 3) + ry_outer_outer)) && ((((((((int)threadIdx.x) * 8) + 13) % 21) / 3) + ry_outer_outer) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 1) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 517) / 3) * 7)) + (ry_outer_ [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 518)] = (((((1 <= (ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 2) % 7))) && ((ry_outer_outer + (((((((int)threadIdx.x) * 8) + 512) / 3) + 2) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + (((((int)threadIdx.x) * 2) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + ((((((int)threadIdx.x) * 8) + 512) / 3) * 7)) [...]
+ }
+ if (((int)threadIdx.x) < 20) {
+ pad_temp_shared[((((int)threadIdx.x) * 8) + 519)] = (((((1 <= (ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 5) % 7))) && ((ry_outer_outer + ((((((int)threadIdx.x) * 8) / 3) + 5) % 7)) < 8)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) * 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 1568) + (((((int)threadIdx.x) * 8) / 3) * 7)) + (ry_outer_outer * 7)) + (((int)blo [...]
+ }
+ kernel_shared[((int)threadIdx.x)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 32)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 64)] = kernel[((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3))];
+ kernel_shared[(((int)threadIdx.x) + 96)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 160)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 4608)];
+ kernel_shared[(((int)threadIdx.x) + 192)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 224)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 9216)];
+ kernel_shared[(((int)threadIdx.x) + 288)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 320)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 352)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 13824)];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 416)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 448)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 18432)];
+ kernel_shared[(((int)threadIdx.x) + 480)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 544)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 23040)];
+ kernel_shared[(((int)threadIdx.x) + 576)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 608)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 27648)];
+ kernel_shared[(((int)threadIdx.x) + 672)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 704)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 736)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 32256)];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 800)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 832)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 36864)];
+ kernel_shared[(((int)threadIdx.x) + 864)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 928)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 41472)];
+ kernel_shared[(((int)threadIdx.x) + 960)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 992)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 46080)];
+ kernel_shared[(((int)threadIdx.x) + 1056)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1088)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1120)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 50688)];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1184)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1216)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 55296)];
+ kernel_shared[(((int)threadIdx.x) + 1248)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1312)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 59904)];
+ kernel_shared[(((int)threadIdx.x) + 1344)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1376)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 64512)];
+ kernel_shared[(((int)threadIdx.x) + 1440)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1472)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1504)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 69120)];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1568)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1600)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1632)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1696)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 78336)];
+ kernel_shared[(((int)threadIdx.x) + 1728)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1760)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 82944)];
+ kernel_shared[(((int)threadIdx.x) + 1824)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1856)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1888)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 87552)];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1952)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 1984)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 92160)];
+ kernel_shared[(((int)threadIdx.x) + 2016)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2080)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 96768)];
+ kernel_shared[(((int)threadIdx.x) + 2112)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2144)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 101376)];
+ kernel_shared[(((int)threadIdx.x) + 2208)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2240)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2272)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 105984)];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2336)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2368)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 110592)];
+ kernel_shared[(((int)threadIdx.x) + 2400)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2464)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 115200)];
+ kernel_shared[(((int)threadIdx.x) + 2496)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2528)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 119808)];
+ kernel_shared[(((int)threadIdx.x) + 2592)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2624)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2656)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 124416)];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2720)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2752)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 129024)];
+ kernel_shared[(((int)threadIdx.x) + 2784)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2848)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 133632)];
+ kernel_shared[(((int)threadIdx.x) + 2880)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2912)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 138240)];
+ kernel_shared[(((int)threadIdx.x) + 2976)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + ((((int)threadIdx.x) / 3) * 9)) + (ry_outer_outer * 3)) + (((int)threadIdx.x) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3008)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 32) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 2) % 3)) + 142848)];
+ kernel_shared[(((int)threadIdx.x) + 3040)] = kernel[(((((((((int)blockIdx.x) / 7) * 147456) + (rc_outer_outer * 288)) + (((((int)threadIdx.x) + 64) / 3) * 9)) + (ry_outer_outer * 3)) + ((((int)threadIdx.x) + 1) % 3)) + 142848)];
+ __syncthreads();
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 96)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 96) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 96) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 96) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 96) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 96) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 96) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 96) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 96) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 96) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 96) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 96) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 96) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 96) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 96) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 96) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 96) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 96) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 96) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 96) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 96) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 96) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 96) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 96) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 96) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 96) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 96) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 96) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 96) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 96) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[216] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[219] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[222] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[225] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[228] * kernel_shared[((((int)threadIdx.x) * 96) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[217] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[220] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[223] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[226] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[229] * kernel_shared[((((int)threadIdx.x) * 96) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[218] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[221] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[224] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[227] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[230] * kernel_shared[((((int)threadIdx.x) * 96) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[231] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[234] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[237] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[240] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[243] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[246] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[249] * kernel_shared[((((int)threadIdx.x) * 96) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[232] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[235] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[238] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[241] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[244] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[247] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[250] * kernel_shared[((((int)threadIdx.x) * 96) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[233] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[236] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[239] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[242] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[245] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[248] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[251] * kernel_shared[((((int)threadIdx.x) * 96) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[252] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[255] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[258] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[261] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[264] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[267] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[270] * kernel_shared[((((int)threadIdx.x) * 96) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[253] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[256] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[259] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[262] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[265] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[268] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[271] * kernel_shared[((((int)threadIdx.x) * 96) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[254] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[257] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[260] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[263] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[266] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[269] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[272] * kernel_shared[((((int)threadIdx.x) * 96) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[273] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[276] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[279] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[282] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[285] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[288] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[291] * kernel_shared[((((int)threadIdx.x) * 96) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[274] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[277] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[280] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[283] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[286] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[289] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[292] * kernel_shared[((((int)threadIdx.x) * 96) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[275] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[278] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[281] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[284] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[287] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[290] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[293] * kernel_shared[((((int)threadIdx.x) * 96) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[294] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[297] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[300] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[303] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[306] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[309] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[312] * kernel_shared[((((int)threadIdx.x) * 96) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[295] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[298] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[301] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[304] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[307] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[310] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[313] * kernel_shared[((((int)threadIdx.x) * 96) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[296] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[299] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[302] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[305] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[308] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[311] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[314] * kernel_shared[((((int)threadIdx.x) * 96) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[315] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[318] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[321] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[324] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[327] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[330] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[333] * kernel_shared[((((int)threadIdx.x) * 96) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[316] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[319] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[322] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[325] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[328] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[331] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[334] * kernel_shared[((((int)threadIdx.x) * 96) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[317] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[320] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[323] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[326] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[329] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[332] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[335] * kernel_shared[((((int)threadIdx.x) * 96) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[336] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[339] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[342] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[345] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[348] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[351] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[354] * kernel_shared[((((int)threadIdx.x) * 96) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[337] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[340] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[343] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[346] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[349] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[352] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[355] * kernel_shared[((((int)threadIdx.x) * 96) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[338] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[341] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[344] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[347] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[350] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[353] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[356] * kernel_shared[((((int)threadIdx.x) * 96) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[357] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[360] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[363] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[366] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[369] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[372] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[375] * kernel_shared[((((int)threadIdx.x) * 96) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[358] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[361] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[364] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[367] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[370] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[373] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[376] * kernel_shared[((((int)threadIdx.x) * 96) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[359] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[362] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[365] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[368] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[371] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[374] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[377] * kernel_shared[((((int)threadIdx.x) * 96) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[378] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[381] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[384] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[387] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[390] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[393] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[396] * kernel_shared[((((int)threadIdx.x) * 96) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[379] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[382] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[385] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[388] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[391] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[394] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[397] * kernel_shared[((((int)threadIdx.x) * 96) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[380] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[383] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[386] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[389] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[392] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[395] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[398] * kernel_shared[((((int)threadIdx.x) * 96) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[399] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[402] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[405] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[408] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[411] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[414] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[417] * kernel_shared[((((int)threadIdx.x) * 96) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[400] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[403] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[406] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[409] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[412] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[415] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[418] * kernel_shared[((((int)threadIdx.x) * 96) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[401] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[404] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[407] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[410] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[413] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[416] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[419] * kernel_shared[((((int)threadIdx.x) * 96) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[420] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[423] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[426] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[429] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[432] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[435] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[438] * kernel_shared[((((int)threadIdx.x) * 96) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[421] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[424] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[427] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[430] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[433] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[436] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[439] * kernel_shared[((((int)threadIdx.x) * 96) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[422] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[425] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[428] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[431] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[434] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[437] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[440] * kernel_shared[((((int)threadIdx.x) * 96) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[441] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[444] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[447] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[450] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[453] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[456] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[459] * kernel_shared[((((int)threadIdx.x) * 96) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[442] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[445] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[448] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[451] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[454] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[457] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[460] * kernel_shared[((((int)threadIdx.x) * 96) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[443] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[446] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[449] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[452] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[455] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[458] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[461] * kernel_shared[((((int)threadIdx.x) * 96) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[462] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[465] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[468] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[471] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[474] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[477] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[480] * kernel_shared[((((int)threadIdx.x) * 96) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[463] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[466] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[469] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[472] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[475] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[478] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[481] * kernel_shared[((((int)threadIdx.x) * 96) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[464] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[467] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[470] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[473] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[476] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[479] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[482] * kernel_shared[((((int)threadIdx.x) * 96) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[483] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[486] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[489] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[492] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[495] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[498] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[501] * kernel_shared[((((int)threadIdx.x) * 96) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[484] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[487] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[490] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[493] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[496] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[499] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[502] * kernel_shared[((((int)threadIdx.x) * 96) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[485] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[488] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[491] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[494] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[497] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[500] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[503] * kernel_shared[((((int)threadIdx.x) * 96) + 71)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[504] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[507] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[510] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[513] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[516] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[519] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[522] * kernel_shared[((((int)threadIdx.x) * 96) + 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[505] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[508] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[511] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[514] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[517] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[520] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[523] * kernel_shared[((((int)threadIdx.x) * 96) + 73)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[506] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[509] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[512] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[515] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[518] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[521] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[524] * kernel_shared[((((int)threadIdx.x) * 96) + 74)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[525] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[528] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[531] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[534] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[537] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[540] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[543] * kernel_shared[((((int)threadIdx.x) * 96) + 75)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[526] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[529] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[532] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[535] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[538] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[541] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[544] * kernel_shared[((((int)threadIdx.x) * 96) + 76)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[527] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[530] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[533] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[536] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[539] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[542] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[545] * kernel_shared[((((int)threadIdx.x) * 96) + 77)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[546] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[549] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[552] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[555] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[558] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[561] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[564] * kernel_shared[((((int)threadIdx.x) * 96) + 78)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[547] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[550] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[553] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[556] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[559] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[562] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[565] * kernel_shared[((((int)threadIdx.x) * 96) + 79)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[548] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[551] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[554] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[557] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[560] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[563] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[566] * kernel_shared[((((int)threadIdx.x) * 96) + 80)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[567] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[570] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[573] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[576] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[579] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[582] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[585] * kernel_shared[((((int)threadIdx.x) * 96) + 81)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[568] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[571] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[574] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[577] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[580] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[583] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[586] * kernel_shared[((((int)threadIdx.x) * 96) + 82)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[569] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[572] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[575] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[578] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[581] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[584] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[587] * kernel_shared[((((int)threadIdx.x) * 96) + 83)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[588] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[591] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[594] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[597] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[600] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[603] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[606] * kernel_shared[((((int)threadIdx.x) * 96) + 84)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[589] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[592] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[595] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[598] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[601] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[604] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[607] * kernel_shared[((((int)threadIdx.x) * 96) + 85)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[590] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[593] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[596] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[599] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[602] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[605] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[608] * kernel_shared[((((int)threadIdx.x) * 96) + 86)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[609] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[612] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[615] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[618] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[621] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[624] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[627] * kernel_shared[((((int)threadIdx.x) * 96) + 87)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[610] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[613] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[616] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[619] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[622] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[625] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[628] * kernel_shared[((((int)threadIdx.x) * 96) + 88)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[611] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[614] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[617] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[620] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[623] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[626] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[629] * kernel_shared[((((int)threadIdx.x) * 96) + 89)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[630] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[633] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[636] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[639] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[642] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[645] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[648] * kernel_shared[((((int)threadIdx.x) * 96) + 90)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[631] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[634] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[637] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[640] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[643] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[646] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[649] * kernel_shared[((((int)threadIdx.x) * 96) + 91)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[632] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[635] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[638] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[641] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[644] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[647] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[650] * kernel_shared[((((int)threadIdx.x) * 96) + 92)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[651] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[654] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[657] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[660] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[663] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[666] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[669] * kernel_shared[((((int)threadIdx.x) * 96) + 93)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[652] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[655] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[658] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[661] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[664] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[667] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[670] * kernel_shared[((((int)threadIdx.x) * 96) + 94)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[653] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[656] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[659] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[662] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[665] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[668] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[671] * kernel_shared[((((int)threadIdx.x) * 96) + 95)]));
}
}
- for (int i1_inner = 0; i1_inner < 8; ++i1_inner) {
- compute[((((((int)blockIdx.x) * 1568) + ((((int)threadIdx.x) / 49) * 392)) + (i1_inner * 49)) + (((int)threadIdx.x) % 49))] = max((conv2d_nchw[i1_inner] + bias[(((((int)blockIdx.x) * 32) + ((((int)threadIdx.x) / 49) * 8)) + 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);
}
}
</pre></div>
@@ -825,7 +2421,7 @@ 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 35.281 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 36.299 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e3e540f3b477c0c52d8eb73e674e8ffd/tune_conv2d_layer_cuda.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_conv2d_layer_cuda.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
index d6fd76e4b..a587a8aee 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.5492 9.5289 9.5905 9.5283 0.0292
+ 10.1770 10.1816 10.2300 10.1194 0.0453
</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 a0f907d30..af236cfdb 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -920,7 +920,7 @@ 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)
- 754.7435 755.0369 755.3552 753.8383 0.6531
+ 756.4694 756.3174 758.9303 754.1606 1.9502
</pre></div>
</div>
</div>
@@ -942,7 +942,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 21.177 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.969 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autoscheduler-tune-network-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/e416b94ca1090b0897c0f6e0df95b911/tune_network_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">tune_network_x86.py</span></code></a></p>
diff --git a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
index e7edd40e7..72d43c60a 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -620,78 +620,27 @@ 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_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_8: placeholder_18: Buffer(placeholder_13, int32, [33], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], [])} {
- for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
- allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ 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: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [64]), storage_scope = global;
+ for (i1.outer: int32, 0, 16) {
for (i.outer.inner: int32, 0, 2) {
for (nb_j.inner: int32, 0, 2) {
- for (i.inner.init: int32, 0, 16) {
- let cse_var_1: int32 = (((i.outer.inner*512) + (i.inner.init*32)) + (nb_j.inner*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
- }
+ for (j.init: int32, 0, 16) {
+ compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
}
- for (elem_idx: int32, 0, let cse_var_2: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_2 + 1)] - placeholder_3[cse_var_2])) {
- for (i.inner: int32, 0, 16) {
- let cse_var_21: int32 = (elem_idx*16)
- let cse_var_20: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
- let cse_var_19: int32 = (((i.outer.inner*512) + (i.inner*32)) + (nb_j.inner*16))
- let cse_var_18: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.outer.inner*4096)) + (i.inner*256))
- let cse_var_17: int32 = (cse_var_19 + 9)
- let cse_var_16: int32 = (cse_var_19 + 8)
- let cse_var_15: int32 = (cse_var_19 + 7)
- let cse_var_14: int32 = (cse_var_19 + 6)
- let cse_var_13: int32 = (cse_var_19 + 5)
- let cse_var_12: int32 = (cse_var_19 + 4)
- let cse_var_11: int32 = (cse_var_19 + 3)
- let cse_var_10: int32 = (cse_var_19 + 2)
- let cse_var_9: int32 = (cse_var_19 + 15)
- let cse_var_8: int32 = (cse_var_19 + 14)
- let cse_var_7: int32 = (cse_var_19 + 13)
- let cse_var_6: int32 = (cse_var_19 + 12)
- let cse_var_5: int32 = (cse_var_19 + 11)
- let cse_var_4: int32 = (cse_var_19 + 10)
- let cse_var_3: int32 = (cse_var_19 + 1)
- {
- compute_5[cse_var_19] = (compute_5[cse_var_19] + (placeholder_1[((placeholder_3[cse_var_20]*16) + cse_var_21)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_3] = (compute_5[cse_var_3] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 1)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_10] = (compute_5[cse_var_10] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 2)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_11] = (compute_5[cse_var_11] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 3)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_12] = (compute_5[cse_var_12] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 4)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_13] = (compute_5[cse_var_13] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 5)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_14] = (compute_5[cse_var_14] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 6)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_15] = (compute_5[cse_var_15] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 7)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_16] = (compute_5[cse_var_16] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 8)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_17] = (compute_5[cse_var_17] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 9)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_4] = (compute_5[cse_var_4] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 10)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_5] = (compute_5[cse_var_5] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 11)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_6] = (compute_5[cse_var_6] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 12)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_7] = (compute_5[cse_var_7] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 13)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_8] = (compute_5[cse_var_8] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 14)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- compute_5[cse_var_9] = (compute_5[cse_var_9] + (placeholder_1[(((placeholder_3[cse_var_20]*16) + cse_var_21) + 15)]*max(placeholder[(cse_var_18 + placeholder_2[(placeholder_3[cse_var_20] + elem_idx)])], 0f32)))
- }
+ for (elem_idx: int32, 0, let cse_var_1: int32 = ((i1.outer*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (j: int32, 0, 16) {
+ let cse_var_3: int32 = ((i1.outer*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.outer.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((i0.outer*512) + (i.outer.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- for (i0.inner: int32, 0, 32) {
- let cse_var_22: int32 = (((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32))
- compute[ramp(cse_var_22, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_22, 1, 32)]), broadcast(0f32, 32))
+ for (i0.inner: int32, 0, 2) {
+ let cse_var_4: int32 = (((i0.outer*1024) + (i0.inner*512)) + (i1.outer*32))
+ compute[ramp(cse_var_4, 1, 32)] = max((compute_5[ramp((i0.inner*32), 1, 32)] + placeholder_4[ramp(cse_var_4, 1, 32)]), broadcast(0f32, 32))
}
}
}
@@ -729,7 +678,7 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.719 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.902 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 2c95225dd..4ed19cc88 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:44.125</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.177</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:44.090</p></td>
+<td><p>00:43.145</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_relay_x86.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-x86-py"><span class="std std-ref">Auto-tuning a Convolutional Network for x86 CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_x86.py</span></code>)</p></td>
-<td><p>00:00.021</p></td>
+<td><p>00:00.019</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-relay-cuda-py"><span class="std std-ref">Auto-tuning a Convolutional Network for NVIDIA GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_cuda.py</span></code>)</p></td>
diff --git a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
index 8c14d1e13..797f8f54f 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1164,8 +1164,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 111.88/111.88 result: MeasureResult(costs=(0.002069203402597403,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8920879364013672, timestamp=1656083567.3411033) [('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: 0.00/111.88 result: Traceback (most recent call last):
+No: 6 GFLOPS: 109.11/109.11 result: MeasureResult(costs=(0.002121732916666667,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6635711193084717, timestamp=1656094762.5332358) [('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: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1288,7 +1288,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1411,7 +1411,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1534,7 +1534,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/109.11 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
@@ -1552,7 +1552,7 @@ No: 10 GFLOPS: 0.00/111.88 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: 0.00/111.88 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1675,7 +1675,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1798,7 +1798,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1921,7 +1921,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2044,7 +2044,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2167,7 +2167,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2290,7 +2290,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2413,7 +2413,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2536,7 +2536,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/111.88 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/109.11 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2624,7 +2624,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f01f7cfbfa2
+ 12: 0x00007f7e217a3fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2689,7 +2689,7 @@ 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: 144.04/144.04 result: MeasureResult(costs=(0.0016072552380952381,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1629483699798584, timestamp=1656083593.7130096) [('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: 141.78/141.78 result: MeasureResult(costs=(0.0016327872741935482,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.1234588623046875, timestamp=1656094788.7532756) [('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,
@@ -2730,7 +2730,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.002005
+Time cost of this operator: 0.002009
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-tune-with-autotvm-tune-conv2d-cuda-py">
diff --git a/docs/how_to/work_with_microtvm/micro_autotune.html b/docs/how_to/work_with_microtvm/micro_autotune.html
index 5b5f533c1..4340a7fb7 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -578,10 +578,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 310.6 98.678 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.259 1.036 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.286 (1, 1, 10, 10, 3) 1 1
-Total_time - 314.76 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 312.7 98.727 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.106 0.981 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.927 0.293 (1, 1, 10, 10, 3) 1 1
+Total_time - 316.733 - - - -
</pre></div>
</div>
</div>
@@ -634,10 +634,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 122.5 97.82 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.829 1.461 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.719 (1, 1, 10, 10, 3) 1 1
-Total_time - 125.23 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 192.2 98.556 (1, 1, 10, 10, 6) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.982 1.017 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.834 0.428 (1, 3, 10, 10, 1) 1 1
+Total_time - 195.017 - - - -
</pre></div>
</div>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-autotune-py">
diff --git a/docs/how_to/work_with_microtvm/micro_train.html b/docs/how_to/work_with_microtvm/micro_train.html
index 3b63c5f41..09cb2e691 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -510,7 +510,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpcyl1ibri/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmpcbeckp09/images/random'
</pre></div>
</div>
</div>
@@ -570,8 +570,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpcyl1ibri/images/target contains 8144 images
-/tmp/tmpcyl1ibri/images/random contains 5000 images
+<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmpcbeckp09/images/target contains 8144 images
+/tmp/tmpcbeckp09/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -683,13 +683,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2194 - accuracy: 0.9229 - val_loss: 0.1428 - val_accuracy: 0.9558
+328/328 - 55s - loss: 0.2223 - accuracy: 0.9234 - val_loss: 0.1299 - val_accuracy: 0.9596
Epoch 2/3
-328/328 - 52s - loss: 0.0956 - accuracy: 0.9650 - val_loss: 0.1064 - val_accuracy: 0.9656
+328/328 - 52s - loss: 0.1018 - accuracy: 0.9615 - val_loss: 0.1280 - val_accuracy: 0.9615
Epoch 3/3
-328/328 - 52s - loss: 0.0637 - accuracy: 0.9767 - val_loss: 0.1252 - val_accuracy: 0.9619
+328/328 - 52s - loss: 0.0694 - accuracy: 0.9742 - val_loss: 0.1528 - val_accuracy: 0.9452
-<keras.callbacks.History object at 0x7f9d640bbbd0>
+<keras.callbacks.History object at 0x7f675d8a59d0>
</pre></div>
</div>
</div>
@@ -951,7 +951,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 40.201 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 7 minutes 59.583 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-how-to-work-with-microtvm-micro-train-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/b52cec46baf4f78d6bcd94cbe269c8a6/micro_train.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">micro_train.py</span></code></a></p>
diff --git a/docs/how_to/work_with_microtvm/sg_execution_times.html b/docs/how_to/work_with_microtvm/sg_execution_times.html
index 5a150c519..181be64fb 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>08:29.010</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>08:45.837</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,15 +331,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_train.html#sphx-glr-how-to-work-with-microtvm-micro-train-py"><span class="std std-ref">Training Vision Models for microTVM on Arduino</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_train.py</span></code>)</p></td>
-<td><p>07:40.201</p></td>
+<td><p>07:59.583</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_autotune.html#sphx-glr-how-to-work-with-microtvm-micro-autotune-py"><span class="std std-ref">Autotuning with microTVM</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_autotune.py</span></code>)</p></td>
-<td><p>00:45.152</p></td>
+<td><p>00:42.799</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="micro_tflite.html#sphx-glr-how-to-work-with-microtvm-micro-tflite-py"><span class="std std-ref">microTVM with TFLite Models</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_tflite.py</span></code>)</p></td>
-<td><p>00:03.656</p></td>
+<td><p>00:03.455</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="micro_ethosu.html#sphx-glr-how-to-work-with-microtvm-micro-ethosu-py"><span class="std std-ref">Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN</span></a> (<code class="docutils literal notranslate"><span class="pre">micro_ethosu.py</span></code>)</p></td>
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 3a2b5e70a..fea554e81 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:11.794</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:09.539</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:10.225</p></td>
+<td><p>00:08.075</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="build_gcn.html#sphx-glr-how-to-work-with-relay-build-gcn-py"><span class="std std-ref">Building a Graph Convolutional Network</span></a> (<code class="docutils literal notranslate"><span class="pre">build_gcn.py</span></code>)</p></td>
-<td><p>00:01.564</p></td>
+<td><p>00:01.459</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="using_relay_viz.html#sphx-glr-how-to-work-with-relay-using-relay-viz-py"><span class="std std-ref">Use Relay Visualizer to Visualize Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_relay_viz.py</span></code>)</p></td>
diff --git a/docs/how_to/work_with_schedules/intrin_math.html b/docs/how_to/work_with_schedules/intrin_math.html
index 87514280e..150d659f0 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -515,7 +515,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f9cbc9f79e0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f66d2f2fb90>
</pre></div>
</div>
<p>Register the rule to TVM with override option to override existing rule.
diff --git a/docs/how_to/work_with_schedules/sg_execution_times.html b/docs/how_to/work_with_schedules/sg_execution_times.html
index 53d241903..b9860fed8 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:04.299</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.018</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -331,35 +331,35 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="intrin_math.html#sphx-glr-how-to-work-with-schedules-intrin-math-py"><span class="std std-ref">Intrinsics and Math Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">intrin_math.py</span></code>)</p></td>
-<td><p>00:01.982</p></td>
+<td><p>00:01.886</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:01.067</p></td>
+<td><p>00:00.920</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="reduction.html#sphx-glr-how-to-work-with-schedules-reduction-py"><span class="std std-ref">Reduction</span></a> (<code class="docutils literal notranslate"><span class="pre">reduction.py</span></code>)</p></td>
-<td><p>00:00.545</p></td>
+<td><p>00:00.524</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="scan.html#sphx-glr-how-to-work-with-schedules-scan-py"><span class="std std-ref">Scan and Recurrent Kernel</span></a> (<code class="docutils literal notranslate"><span class="pre">scan.py</span></code>)</p></td>
-<td><p>00:00.530</p></td>
+<td><p>00:00.517</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="extern_op.html#sphx-glr-how-to-work-with-schedules-extern-op-py"><span class="std std-ref">External Tensor Functions</span></a> (<code class="docutils literal notranslate"><span class="pre">extern_op.py</span></code>)</p></td>
-<td><p>00:00.101</p></td>
+<td><p>00:00.098</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="schedule_primitives.html#sphx-glr-how-to-work-with-schedules-schedule-primitives-py"><span class="std std-ref">Schedule Primitives in TVM</span></a> (<code class="docutils literal notranslate"><span class="pre">schedule_primitives.py</span></code>)</p></td>
-<td><p>00:00.034</p></td>
+<td><p>00:00.033</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="tedd.html#sphx-glr-how-to-work-with-schedules-tedd-py"><span class="std std-ref">Use Tensor Expression Debug Display (TEDD) for Visualization</span></a> (<code class="docutils literal notranslate"><span class="pre">tedd.py</span></code>)</p></td>
-<td><p>00:00.027</p></td>
+<td><p>00:00.028</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><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></td>
-<td><p>00:00.013</p></td>
+<td><p>00:00.012</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/how_to/work_with_schedules/tensorize.html b/docs/how_to/work_with_schedules/tensorize.html
index d7a195d41..7bc3114a0 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -571,7 +571,7 @@ 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/tmpnq81740h/input0.cc'\nsource_filename = \"/tmp/tmpnq81740h/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/tmpt4zzdkfh/input0.cc'\nsource_filename = \"/tmp/tmpt4zzdkfh/input0.cc\"\ntarget datalayout = \"e-m:e-i64:64-f80:128-n8:16:32:64-S128\"\ntarget triple = \"x86_64-pc-linux-gnu\"\n\n; Function Attrs: noinline nounwind optnone uwtable\ndefine dso_local i32 @gemv_update(float*, float*, float*, i32, i32, i32) #0 {\n %7 = allo [...]
for (i, 0, 1024) {
for (j.outer: int32, 0, 32) {
@tir.call_extern("gemv_update", @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), C_2, ((i*512) + (j.outer*16)), 16, 2, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), A_2, (i*64), 64, 1, dtype=handle), @tir.tvm_access_ptr(@tir.type_annotation(, dtype=float32), B_2, (j.outer*1024), 1024, 1, dtype=handle), 16, 64, 64, dtype=int32)
diff --git a/docs/reference/api/python/auto_scheduler.html b/docs/reference/api/python/auto_scheduler.html
index 98427ff1a..29ff24c6f 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1737,7 +1737,7 @@ 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">
@@ -1774,7 +1774,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 29a3e6370..97d732375 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/ed3294fb3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 b0c433669..8612fa7a4 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/ed3294fb3/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 736686091..adfafa07c 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/ed3294fb3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 5602c8c2f..a96477d80 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/ed3294fb3/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 ba9da0d85..8ae87bbab 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/ed3294fb3/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 5007236bb..dad1a479f 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/ed3294fb3/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 5ae93eb78..451a272f1 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/ed3294fb3/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 52fd10e56..ed958ef83 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/ed3294fb3/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 36d67b8cd..a151e9220 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/ed3294fb3/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 bf43cea9b..57cb4c4fd 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/ed3294fb3/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 c4b6bb153..7a21aff74 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/ed3294fb3/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 46d13abe2..929d8e074 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/ed3294fb3/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 8f4f8ff0d..4ca519300 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/ed3294fb3/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 7a0a3faff..e986dfd99 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/ed3294fb3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 ee67a14f6..cd8303e30 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/ed3294fb3/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 6a50e0155..32e3deae0 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/ed3294fb3/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 e4ded0f7b..673bb39fb 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/ed3294fb3/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 0e7118fd5..15785d8b7 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/ed3294fb3/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 405958101..b2ddd7825 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/ed3294fb3/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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 9dcf4c7ec..edd74edc6 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/ed3294fb3/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/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/ed3294fb3/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
</ul>
</aside>
</section>
@@ -140,7 +140,7 @@
<div class="tsd-signature tsd-kind-icon">I32<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
</ul>
</aside>
</section>
@@ -150,7 +150,7 @@
<div class="tsd-signature tsd-kind-icon">I64<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
</ul>
</aside>
</section>
@@ -160,7 +160,7 @@
<div class="tsd-signature tsd-kind-icon">TVMValue<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
</ul>
</aside>
</section>
@@ -170,7 +170,7 @@
<div class="tsd-signature tsd-kind-icon">U16<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
</ul>
</aside>
</section>
@@ -180,7 +180,7 @@
<div class="tsd-signature tsd-kind-icon">U8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/index.html b/docs/reference/api/typedoc/index.html
index 59f231d4d..81341681d 100644
--- a/docs/reference/api/typedoc/index.html
+++ b/docs/reference/api/typedoc/index.html
@@ -174,7 +174,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Alloc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>shape<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, ndim<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeCode<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, dtypeBits<span class="tsd [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -238,7 +238,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>Bytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">num [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -282,7 +282,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>From<wbr>To<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>from<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, to<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-sig [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -326,7 +326,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Copy<wbr>ToBytes<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, data<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nbytes<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</sp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -370,7 +370,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMArray<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>handle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -406,7 +406,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMBackend<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number< [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -458,7 +458,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCFunc<wbr>Set<wbr>Return<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ret<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -506,7 +506,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMCb<wbr>Arg<wbr>ToReturn<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>value<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, code<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span c [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -545,7 +545,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Call<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, argValues<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCode<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-t [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -601,7 +601,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>func<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -637,7 +637,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Get<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span cla [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -676,7 +676,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>List<wbr>Global<wbr>Names<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>outSize<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, outArray<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -715,7 +715,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMFunc<wbr>Register<wbr>Global<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>name<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, f<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, override<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</spa [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -758,7 +758,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMGet<wbr>Last<wbr>Error<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -788,7 +788,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Free<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -824,7 +824,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Get<wbr>Function<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, funcName<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, queryImports<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">numbe [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -872,7 +872,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMMod<wbr>Import<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>mod<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, dep<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-si [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -912,7 +912,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMSynchronize<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>deviceType<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, deviceId<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, stream<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signatur [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -954,7 +954,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Alloc<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>size<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -990,7 +990,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Free<wbr>Space<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>ptr<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1026,7 +1026,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>Func<wbr>Create<wbr>FromCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resource<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, out<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> =&g [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1066,7 +1066,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>args<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, typeCodes<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a>, nargs<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">number</span>, [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1118,7 +1118,7 @@
<div class="tsd-signature tsd-kind-icon">FTVMWasm<wbr>PackedCFunc<wbr>Finalizer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>resourceHandle<span class="tsd-signature-symbol">: </span><a href="index.html#pointer" class="tsd-signature-type">Pointer</a><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1154,7 +1154,7 @@
<div class="tsd-signature tsd-kind-icon">GPUPointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1169,7 +1169,7 @@
<div class="tsd-signature tsd-kind-icon">Packed<wbr>Func<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">...</span>args<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol"> & </span><a href="interfaces/disp [...]
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L36">runtime.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1184,7 +1184,7 @@
<div class="tsd-signature tsd-kind-icon">Pointer<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1199,7 +1199,7 @@
<div class="tsd-signature tsd-kind-icon">Ptr<wbr>Offset<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1217,7 +1217,7 @@
<div class="tsd-signature tsd-kind-icon">RPC_<wbr>MAGIC<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">1045105</span><span class="tsd-signature-symbol"> = 1045105</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1239,7 +1239,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/support.ts#L25">support.ts:25</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1271,7 +1271,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/support.ts#L39">support.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1300,7 +1300,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/support.ts#L52">support.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1337,7 +1337,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/compact.ts#L38">compact.ts:38</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1368,7 +1368,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1390,7 +1390,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/environment.ts#L32">environment.ts:32</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1421,7 +1421,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/compact.ts#L24">compact.ts:24</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1443,7 +1443,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1508,7 +1508,7 @@
<li class="tsd-description">
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/support.ts#L62">support.ts:62</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -1530,7 +1530,7 @@
<div class="tsd-signature tsd-kind-icon">DLData<wbr>Type<wbr>Code<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L246">runtime.ts:246</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1539,7 +1539,7 @@
<div class="tsd-signature tsd-kind-icon">0<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "int"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L247">runtime.ts:247</a></li>
</ul>
</aside>
</section>
@@ -1549,7 +1549,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "uint"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L248">runtime.ts:248</a></li>
</ul>
</aside>
</section>
@@ -1559,7 +1559,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "float"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L249">runtime.ts:249</a></li>
</ul>
</aside>
</section>
@@ -1569,7 +1569,7 @@
<div class="tsd-signature tsd-kind-icon">3<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "handle"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L250">runtime.ts:250</a></li>
</ul>
</aside>
</section>
@@ -1580,7 +1580,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Enum<wbr>ToStr<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L175">runtime.ts:175</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1589,7 +1589,7 @@
<div class="tsd-signature tsd-kind-icon">1<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L176">runtime.ts:176</a></li>
</ul>
</aside>
</section>
@@ -1599,7 +1599,7 @@
<div class="tsd-signature tsd-kind-icon">15<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "webgpu"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L180">runtime.ts:180</a></li>
</ul>
</aside>
</section>
@@ -1609,7 +1609,7 @@
<div class="tsd-signature tsd-kind-icon">2<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "cuda"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L177">runtime.ts:177</a></li>
</ul>
</aside>
</section>
@@ -1619,7 +1619,7 @@
<div class="tsd-signature tsd-kind-icon">4<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "opencl"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L178">runtime.ts:178</a></li>
</ul>
</aside>
</section>
@@ -1629,7 +1629,7 @@
<div class="tsd-signature tsd-kind-icon">8<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span><span class="tsd-signature-symbol"> = "metal"</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L179">runtime.ts:179</a></li>
</ul>
</aside>
</section>
@@ -1640,7 +1640,7 @@
<div class="tsd-signature tsd-kind-icon">Device<wbr>Str<wbr>ToEnum<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">object</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L183">runtime.ts:183</a></li>
</ul>
</aside>
<section class="tsd-panel tsd-member tsd-kind-variable tsd-parent-kind-object-literal">
@@ -1649,7 +1649,7 @@
<div class="tsd-signature tsd-kind-icon">cl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L186">runtime.ts:186</a></li>
</ul>
</aside>
</section>
@@ -1659,7 +1659,7 @@
<div class="tsd-signature tsd-kind-icon">cpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 1</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L184">runtime.ts:184</a></li>
</ul>
</aside>
</section>
@@ -1669,7 +1669,7 @@
<div class="tsd-signature tsd-kind-icon">cuda<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 2</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L185">runtime.ts:185</a></li>
</ul>
</aside>
</section>
@@ -1679,7 +1679,7 @@
<div class="tsd-signature tsd-kind-icon">metal<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 8</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L189">runtime.ts:189</a></li>
</ul>
</aside>
</section>
@@ -1689,7 +1689,7 @@
<div class="tsd-signature tsd-kind-icon">opencl<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 4</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L187">runtime.ts:187</a></li>
</ul>
</aside>
</section>
@@ -1699,7 +1699,7 @@
<div class="tsd-signature tsd-kind-icon">vulkan<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 7</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L188">runtime.ts:188</a></li>
</ul>
</aside>
</section>
@@ -1709,7 +1709,7 @@
<div class="tsd-signature tsd-kind-icon">webgpu<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">number</span><span class="tsd-signature-symbol"> = 15</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/runtime.ts#L190">runtime.ts:190</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/disposable.html b/docs/reference/api/typedoc/interfaces/disposable.html
index c42cf224d..6e3ab1d43 100644
--- a/docs/reference/api/typedoc/interfaces/disposable.html
+++ b/docs/reference/api/typedoc/interfaces/disposable.html
@@ -113,7 +113,7 @@
<div class="tsd-signature tsd-kind-icon">dispose<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/types.ts#L52">types.ts:52</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/reference/api/typedoc/interfaces/functioninfo.html b/docs/reference/api/typedoc/interfaces/functioninfo.html
index 33e52fd0f..37d73fedd 100644
--- a/docs/reference/api/typedoc/interfaces/functioninfo.html
+++ b/docs/reference/api/typedoc/interfaces/functioninfo.html
@@ -95,7 +95,7 @@
<div class="tsd-signature tsd-kind-icon">arg_<wbr>types<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
</ul>
</aside>
</section>
@@ -105,7 +105,7 @@
<div class="tsd-signature tsd-kind-icon">launch_<wbr>param_<wbr>tags<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Array</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
</ul>
</aside>
</section>
@@ -115,7 +115,7 @@
<div class="tsd-signature tsd-kind-icon">name<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">string</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
</ul>
</aside>
</section>
diff --git a/docs/reference/api/typedoc/interfaces/libraryprovider.html b/docs/reference/api/typedoc/interfaces/libraryprovider.html
index d2fca70c1..a2876aac0 100644
--- a/docs/reference/api/typedoc/interfaces/libraryprovider.html
+++ b/docs/reference/api/typedoc/interfaces/libraryprovider.html
@@ -112,7 +112,7 @@
<div class="tsd-signature tsd-kind-icon">imports<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Record</span><span class="tsd-signature-symbol"><</span><span class="tsd-signature-type">string</span><span class="tsd-signature-symbol">, </span><span class="tsd-signature-type">any</span><span class="tsd-signature-symbol">></span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/types.ts#L34">types.ts:34</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
@@ -127,7 +127,7 @@
<div class="tsd-signature tsd-kind-icon">start<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-symbol">(</span>inst<span class="tsd-signature-symbol">: </span><span class="tsd-signature-type">Instance</span><span class="tsd-signature-symbol">)</span><span class="tsd-signature-symbol"> => </span><span class="tsd-signature-type">void</span></div>
<aside class="tsd-sources">
<ul>
- <li>Defined in <a href="https://github.com/apache/tvm/blob/ed3294fb3/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/f1d30a27b/web/src/types.ts#L39">types.ts:39</a></li>
</ul>
</aside>
<div class="tsd-comment tsd-typography">
diff --git a/docs/searchindex.js b/docs/searchindex.js
index 2d0dde734..c791eb1e8 100644
--- a/docs/searchindex.js
+++ b/docs/searchindex.js
@@ -1 +1 @@
-Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
+Search.setIndex({docnames:["arch/benchmark","arch/convert_layout","arch/debugger","arch/device_target_interactions","arch/frontend/tensorflow","arch/hybrid_script","arch/index","arch/inferbound","arch/introduction_to_module_serialization","arch/microtvm_design","arch/microtvm_project_api","arch/model_library_format","arch/pass_infra","arch/relay_intro","arch/relay_op_strategy","arch/runtime","arch/runtimes/vulkan","arch/security","arch/virtual_machine","contribute/ci","contribute/code_gu [...]
\ No newline at end of file
diff --git a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
index 5b787e07d..2c3ce6415 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:21.115</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:20.783</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:21.109</p></td>
+<td><p>00:20.777</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
-<td><p>00:00.007</p></td>
+<td><p>00:00.006</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index 95e363952..caf0a92aa 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -566,7 +566,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.96s!
+resnet18_v1 inference graph built in 22.49s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_detection.html b/docs/topic/vta/tutorials/frontend/deploy_detection.html
index aaa6f777b..9e8cb65f2 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -584,7 +584,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:411: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 16.12s!
+yolov3-tiny inference graph built in 15.73s!
</pre></div>
</div>
</div>
diff --git a/docs/topic/vta/tutorials/frontend/sg_execution_times.html b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
index ba143de85..6969736ec 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:31.474</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:30.302</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:48.266</p></td>
+<td><p>00:47.768</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="deploy_classification.html#sphx-glr-topic-vta-tutorials-frontend-deploy-classification-py"><span class="std std-ref">Deploy Pretrained Vision Model from MxNet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_classification.py</span></code>)</p></td>
-<td><p>00:43.208</p></td>
+<td><p>00:42.534</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/optimize/sg_execution_times.html b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
index 46d99531d..d90650fe1 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.295</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.268</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -335,7 +335,7 @@
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.414</p></td>
+<td><p>00:00.386</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/topic/vta/tutorials/sg_execution_times.html b/docs/topic/vta/tutorials/sg_execution_times.html
index 33867d0c3..c40246c41 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -322,7 +322,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.764</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.700</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -331,11 +331,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.411</p></td>
+<td><p>00:00.371</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="vta_get_started.html#sphx-glr-topic-vta-tutorials-vta-get-started-py"><span class="std std-ref">Get Started with VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">vta_get_started.py</span></code>)</p></td>
-<td><p>00:00.352</p></td>
+<td><p>00:00.329</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>
diff --git a/docs/tutorial/auto_scheduler_matmul_x86.html b/docs/tutorial/auto_scheduler_matmul_x86.html
index 84cc01b81..815870b0d 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -561,7 +561,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.937 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 93.341 ms
</pre></div>
</div>
</div>
@@ -625,7 +625,6 @@ resume the status and do more 5 trials.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Resume search:
/usr/local/lib/python3.7/dist-packages/xgboost/training.py:17: UserWarning: Old style callback is deprecated. See: https://xgboost.readthedocs.io/en/latest/python/callbacks.html
warnings.warn(f'Old style callback is deprecated. See: {link}', UserWarning)
-*E
</pre></div>
</div>
</div>
@@ -636,7 +635,6 @@ automatically optimize a matrix multiplication, without the need to specify a
search template. It ends a series of examples that starts from the Tensor
Expression (TE) language that demonstrates how TVM can optimize computational
operations.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 3.242 seconds)</p>
<div class="sphx-glr-footer sphx-glr-footer-example docutils container" id="sphx-glr-download-tutorial-auto-scheduler-matmul-x86-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../_downloads/eac4389b114db015e95cb3cdf8b86b83/auto_scheduler_matmul_x86.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">auto_scheduler_matmul_x86.py</span></code></a></p>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index eb67ded7c..9dae4939c 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -660,16 +660,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 9.62/9.62 result: MeasureResult(costs=(0.027897005600000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5816020965576172, timestamp=1656082402.8525405) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.68/9.62 result: MeasureResult(costs=(0.100169451,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.744786024093628, timestamp=1656082404.6205306) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227596202,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5661830902099609, timestamp=1656082405.677771) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.86/11.79 result: MeasureResult(costs=(0.1442381726,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4307260513305664, timestamp=1656082408.1538284) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.66/11.79 result: MeasureResult(costs=(0.07342711160000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3140251636505127, timestamp=1656082409.595319) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.70/11.79 result: MeasureResult(costs=(0.1578412646,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.646113872528076, timestamp=1656082412.8173013) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.76/11.79 result: MeasureResult(costs=(0.3545529498,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.789679288864136, timestamp=1656082419.1845098) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 9.83/11.79 result: MeasureResult(costs=(0.0273171538,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5848524570465088, timestamp=1656082419.786651) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.52/11.79 result: MeasureResult(costs=(0.1770291184,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.944798707962036, timestamp=1656082422.8509488) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.18/11.79 result: MeasureResult(costs=(0.1232330916,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.0778651237487793, timestamp=1656082424.988339) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 10.34/10.34 result: MeasureResult(costs=(0.025971265799999997,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5495269298553467, timestamp=1656093636.995069) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.65/10.34 result: MeasureResult(costs=(0.10123502820000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.765075922012329, timestamp=1656093638.7738595) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.022772455400000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.55118727684021, timestamp=1656093639.8189595) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.56/11.79 result: MeasureResult(costs=(0.172348963,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.8733017444610596, timestamp=1656093643.256166) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.60/11.79 result: MeasureResult(costs=(0.0744695276,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3304519653320312, timestamp=1656093644.7122812) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.78/11.79 result: MeasureResult(costs=(0.15104362659999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.578220844268799, timestamp=1656093647.3361433) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.82/11.79 result: MeasureResult(costs=(0.3274878444,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.3515944480896, timestamp=1656093653.259746) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.04/11.79 result: MeasureResult(costs=(0.0267448458,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5762312412261963, timestamp=1656093653.84942) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.68/11.79 result: MeasureResult(costs=(0.1596127274,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.651829481124878, timestamp=1656093656.6200204) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.26/11.79 result: MeasureResult(costs=(0.11855880939999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.004706621170044, timestamp=1656093658.684421) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
</pre></div>
</div>
<p>With tuning completed, we can choose the configuration from the log file that
diff --git a/docs/tutorial/autotvm_relay_x86.html b/docs/tutorial/autotvm_relay_x86.html
index 3b6d7dcf3..e4e335071 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -542,7 +542,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 496.88231371000256, 'median': 496.1883234000197, 'std': 1.775787691602362}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 497.09820047999983, 'median': 497.0073505500068, 'std': 0.594892070012249}
</pre></div>
</div>
</div>
@@ -697,179 +697,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.41/ 17.41 GFLOPS | Progress: (4/20) | 5.90 s
-[Task 1/25] Current/Best: 6.16/ 17.41 GFLOPS | Progress: (8/20) | 9.31 s
-[Task 1/25] Current/Best: 11.54/ 22.68 GFLOPS | Progress: (12/20) | 11.75 s
-[Task 1/25] Current/Best: 16.74/ 22.74 GFLOPS | Progress: (16/20) | 13.43 s
-[Task 1/25] Current/Best: 11.58/ 23.87 GFLOPS | Progress: (20/20) | 15.16 s Done.
+[Task 1/25] Current/Best: 17.42/ 17.42 GFLOPS | Progress: (4/20) | 6.25 s
+[Task 1/25] Current/Best: 6.17/ 17.42 GFLOPS | Progress: (8/20) | 9.22 s
+[Task 1/25] Current/Best: 11.55/ 22.81 GFLOPS | Progress: (12/20) | 11.63 s
+[Task 1/25] Current/Best: 16.86/ 22.81 GFLOPS | Progress: (16/20) | 13.31 s
+[Task 1/25] Current/Best: 11.63/ 23.87 GFLOPS | Progress: (20/20) | 15.05 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.18/ 12.91 GFLOPS | Progress: (4/20) | 3.78 s
-[Task 2/25] Current/Best: 14.27/ 18.33 GFLOPS | Progress: (8/20) | 5.09 s
-[Task 2/25] Current/Best: 21.24/ 21.24 GFLOPS | Progress: (12/20) | 6.40 s
-[Task 2/25] Current/Best: 12.14/ 21.24 GFLOPS | Progress: (16/20) | 7.66 s
-[Task 2/25] Current/Best: 19.25/ 21.24 GFLOPS | Progress: (20/20) | 9.23 s Done.
+[Task 2/25] Current/Best: 12.18/ 13.11 GFLOPS | Progress: (4/20) | 3.63 s
+[Task 2/25] Current/Best: 13.96/ 18.31 GFLOPS | Progress: (8/20) | 4.93 s
+[Task 2/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (12/20) | 6.24 s
+[Task 2/25] Current/Best: 11.69/ 21.21 GFLOPS | Progress: (16/20) | 7.54 s
+[Task 2/25] Current/Best: 19.08/ 21.21 GFLOPS | Progress: (20/20) | 9.14 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/ 10.52 GFLOPS | Progress: (4/20) | 5.90 s
-[Task 3/25] Current/Best: 15.55/ 16.85 GFLOPS | Progress: (8/20) | 7.84 s
-[Task 3/25] Current/Best: 14.85/ 16.85 GFLOPS | Progress: (12/20) | 9.55 s
-[Task 3/25] Current/Best: 7.17/ 23.78 GFLOPS | Progress: (16/20) | 11.53 s
-[Task 3/25] Current/Best: 12.62/ 23.78 GFLOPS | Progress: (20/20) | 16.03 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.60 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.51/ 16.83 GFLOPS | Progress: (8/20) | 7.78 s
+[Task 3/25] Current/Best: 14.86/ 16.83 GFLOPS | Progress: (12/20) | 9.50 s
+[Task 3/25] Current/Best: 7.19/ 23.81 GFLOPS | Progress: (16/20) | 11.45 s
+[Task 3/25] Current/Best: 12.55/ 23.81 GFLOPS | Progress: (20/20) | 15.95 s Done.
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 4/25] Current/Best: 9.54/ 20.44 GFLOPS | Progress: (4/20) | 2.39 s
-[Task 4/25] Current/Best: 6.65/ 20.44 GFLOPS | Progress: (8/20) | 6.74 s
-[Task 4/25] Current/Best: 21.35/ 21.35 GFLOPS | Progress: (12/20) | 11.32 s
-[Task 4/25] Current/Best: 16.52/ 21.35 GFLOPS | Progress: (16/20) | 13.58 s
-[Task 4/25] Current/Best: 13.29/ 21.35 GFLOPS | Progress: (20/20) | 15.48 s Done.
+[Task 4/25] Current/Best: 9.56/ 20.46 GFLOPS | Progress: (4/20) | 2.37 s
+[Task 4/25] Current/Best: 6.75/ 20.46 GFLOPS | Progress: (8/20) | 6.71 s
+[Task 4/25] Current/Best: 22.08/ 22.08 GFLOPS | Progress: (12/20) | 11.21 s
+[Task 4/25] Current/Best: 17.35/ 22.08 GFLOPS | Progress: (16/20) | 13.45 s
+[Task 4/25] Current/Best: 13.18/ 22.08 GFLOPS | Progress: (20/20) | 15.42 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.45/ 10.12 GFLOPS | Progress: (4/20) | 2.60 s
-[Task 5/25] Current/Best: 11.53/ 11.83 GFLOPS | Progress: (8/20) | 4.68 s
-[Task 5/25] Current/Best: 10.14/ 18.04 GFLOPS | Progress: (12/20) | 7.63 s
-[Task 5/25] Current/Best: 11.67/ 22.42 GFLOPS | Progress: (16/20) | 9.07 s
-[Task 5/25] Current/Best: 11.86/ 22.42 GFLOPS | Progress: (20/20) | 10.95 s Done.
+[Task 5/25] Current/Best: 9.35/ 10.31 GFLOPS | Progress: (4/20) | 2.58 s
+[Task 5/25] Current/Best: 11.53/ 12.40 GFLOPS | Progress: (8/20) | 4.66 s
+[Task 5/25] Current/Best: 11.55/ 17.68 GFLOPS | Progress: (12/20) | 7.73 s
+[Task 5/25] Current/Best: 11.69/ 22.86 GFLOPS | Progress: (16/20) | 9.14 s
+[Task 5/25] Current/Best: 12.01/ 22.86 GFLOPS | Progress: (20/20) | 11.02 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.21/ 20.68 GFLOPS | Progress: (4/20) | 3.99 s
-[Task 6/25] Current/Best: 18.94/ 20.68 GFLOPS | Progress: (8/20) | 5.75 s
-[Task 6/25] Current/Best: 13.14/ 20.68 GFLOPS | Progress: (12/20) | 7.68 s
-[Task 6/25] Current/Best: 19.76/ 20.68 GFLOPS | Progress: (16/20) | 9.93 s
-[Task 6/25] Current/Best: 3.72/ 20.68 GFLOPS | Progress: (20/20) | 12.47 s Done.
+[Task 6/25] Current/Best: 12.21/ 20.70 GFLOPS | Progress: (4/20) | 3.98 s
+[Task 6/25] Current/Best: 18.85/ 20.70 GFLOPS | Progress: (8/20) | 5.74 s
+[Task 6/25] Current/Best: 13.28/ 20.70 GFLOPS | Progress: (12/20) | 7.66 s
+[Task 6/25] Current/Best: 19.84/ 20.70 GFLOPS | Progress: (16/20) | 9.94 s
+[Task 6/25] Current/Best: 3.69/ 20.70 GFLOPS | Progress: (20/20) | 12.48 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.19/ 12.78 GFLOPS | Progress: (4/20) | 3.57 s
-[Task 7/25] Current/Best: 20.20/ 21.06 GFLOPS | Progress: (8/20) | 5.08 s
-[Task 7/25] Current/Best: 16.04/ 21.06 GFLOPS | Progress: (12/20) | 7.00 s
-[Task 7/25] Current/Best: 12.25/ 21.06 GFLOPS | Progress: (16/20) | 9.05 s
-[Task 7/25] Current/Best: 6.33/ 21.69 GFLOPS | Progress: (20/20) | 11.51 s Done.
+[Task 7/25] Current/Best: 11.19/ 12.92 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 7/25] Current/Best: 20.31/ 21.04 GFLOPS | Progress: (8/20) | 5.03 s
+[Task 7/25] Current/Best: 16.12/ 21.04 GFLOPS | Progress: (12/20) | 6.98 s
+[Task 7/25] Current/Best: 12.19/ 21.04 GFLOPS | Progress: (16/20) | 9.01 s
+[Task 7/25] Current/Best: 6.36/ 21.72 GFLOPS | Progress: (20/20) | 11.47 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 9.83/ 14.38 GFLOPS | Progress: (4/20) | 2.96 s
-[Task 8/25] Current/Best: 9.68/ 14.38 GFLOPS | Progress: (8/20) | 7.78 s
-[Task 8/25] Current/Best: 13.18/ 14.38 GFLOPS | Progress: (12/20) | 13.96 s
-[Task 8/25] Current/Best: 18.71/ 18.71 GFLOPS | Progress: (16/20) | 16.05 s
-[Task 8/25] Current/Best: 19.66/ 19.66 GFLOPS | Progress: (20/20) | 22.56 s Done.
+[Task 8/25] Current/Best: 9.64/ 14.07 GFLOPS | Progress: (4/20) | 2.91 s
+[Task 8/25] Current/Best: 9.42/ 14.07 GFLOPS | Progress: (8/20) | 7.75 s
+[Task 8/25] Current/Best: 12.51/ 14.07 GFLOPS | Progress: (12/20) | 13.96 s
+[Task 8/25] Current/Best: 18.40/ 18.40 GFLOPS | Progress: (16/20) | 16.05 s
+[Task 8/25] Current/Best: 19.07/ 19.07 GFLOPS | Progress: (20/20) | 22.52 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.27/ 15.66 GFLOPS | Progress: (4/20) | 11.97 s
-[Task 9/25] Current/Best: 23.47/ 23.47 GFLOPS | Progress: (8/20) | 13.79 s
-[Task 9/25] Current/Best: 8.25/ 23.47 GFLOPS | Progress: (12/20) | 16.16 s
-[Task 9/25] Current/Best: 17.93/ 23.47 GFLOPS | Progress: (16/20) | 18.79 s
-[Task 9/25] Current/Best: 8.98/ 23.47 GFLOPS | Progress: (20/20) | 26.40 s
+[Task 9/25] Current/Best: 14.27/ 15.83 GFLOPS | Progress: (4/20) | 11.94 s
+[Task 9/25] Current/Best: 23.53/ 23.53 GFLOPS | Progress: (8/20) | 13.74 s
+[Task 9/25] Current/Best: 8.22/ 23.53 GFLOPS | Progress: (12/20) | 16.11 s
+[Task 9/25] Current/Best: 17.89/ 23.53 GFLOPS | Progress: (16/20) | 18.77 s
+[Task 9/25] Current/Best: 9.02/ 23.53 GFLOPS | Progress: (20/20) | 26.30 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.27/ 18.27 GFLOPS | Progress: (4/20) | 2.59 s
-[Task 10/25] Current/Best: 15.29/ 18.27 GFLOPS | Progress: (8/20) | 4.16 s
-[Task 10/25] Current/Best: 12.30/ 19.02 GFLOPS | Progress: (12/20) | 5.69 s
-[Task 10/25] Current/Best: 19.06/ 20.12 GFLOPS | Progress: (16/20) | 6.79 s
-[Task 10/25] Current/Best: 8.89/ 20.12 GFLOPS | Progress: (20/20) | 8.34 s Done.
+[Task 10/25] Current/Best: 18.23/ 18.23 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 10/25] Current/Best: 15.53/ 18.23 GFLOPS | Progress: (8/20) | 4.14 s
+[Task 10/25] Current/Best: 11.99/ 18.88 GFLOPS | Progress: (12/20) | 5.66 s
+[Task 10/25] Current/Best: 18.60/ 20.50 GFLOPS | Progress: (16/20) | 6.77 s
+[Task 10/25] Current/Best: 8.80/ 20.50 GFLOPS | Progress: (20/20) | 8.32 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.28/ 18.16 GFLOPS | Progress: (4/20) | 3.28 s
-[Task 11/25] Current/Best: 16.64/ 18.16 GFLOPS | Progress: (8/20) | 5.99 s
-[Task 11/25] Current/Best: 17.98/ 18.16 GFLOPS | Progress: (12/20) | 8.00 s
-[Task 11/25] Current/Best: 13.41/ 21.21 GFLOPS | Progress: (16/20) | 10.79 s
-[Task 11/25] Current/Best: 19.32/ 21.54 GFLOPS | Progress: (20/20) | 12.82 s Done.
+[Task 11/25] Current/Best: 11.13/ 18.14 GFLOPS | Progress: (4/20) | 3.33 s
+[Task 11/25] Current/Best: 16.57/ 18.14 GFLOPS | Progress: (8/20) | 6.04 s
+[Task 11/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (12/20) | 8.07 s
+[Task 11/25] Current/Best: 13.45/ 21.19 GFLOPS | Progress: (16/20) | 10.84 s
+[Task 11/25] Current/Best: 19.45/ 21.41 GFLOPS | Progress: (20/20) | 12.89 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.82/ 17.99 GFLOPS | Progress: (4/20) | 5.37 s
-[Task 12/25] Current/Best: 5.22/ 17.99 GFLOPS | Progress: (8/20) | 9.10 s
-[Task 12/25] Current/Best: 18.76/ 18.98 GFLOPS | Progress: (12/20) | 11.08 s
-[Task 12/25] Current/Best: 15.37/ 18.98 GFLOPS | Progress: (16/20) | 13.82 s
-[Task 12/25] Current/Best: 15.12/ 18.98 GFLOPS | Progress: (20/20) | 15.74 s Done.
+[Task 12/25] Current/Best: 7.79/ 18.03 GFLOPS | Progress: (4/20) | 5.44 s
+[Task 12/25] Current/Best: 5.22/ 18.03 GFLOPS | Progress: (8/20) | 9.14 s
+[Task 12/25] Current/Best: 18.93/ 18.98 GFLOPS | Progress: (12/20) | 11.14 s
+[Task 12/25] Current/Best: 15.16/ 18.98 GFLOPS | Progress: (16/20) | 13.94 s
+[Task 12/25] Current/Best: 15.12/ 19.06 GFLOPS | Progress: (20/20) | 15.86 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.87/ 17.34 GFLOPS | Progress: (4/20) | 3.66 s
-[Task 13/25] Current/Best: 15.12/ 20.96 GFLOPS | Progress: (8/20) | 6.11 s
-[Task 13/25] Current/Best: 19.59/ 21.65 GFLOPS | Progress: (12/20) | 9.02 s
-[Task 13/25] Current/Best: 12.23/ 21.65 GFLOPS | Progress: (16/20) | 12.39 s
-[Task 13/25] Current/Best: 18.64/ 21.65 GFLOPS | Progress: (20/20) | 14.67 s Done.
+[Task 13/25] Current/Best: 8.65/ 17.37 GFLOPS | Progress: (4/20) | 3.68 s
+[Task 13/25] Current/Best: 15.96/ 20.92 GFLOPS | Progress: (8/20) | 6.09 s
+[Task 13/25] Current/Best: 19.62/ 21.66 GFLOPS | Progress: (12/20) | 8.95 s
+[Task 13/25] Current/Best: 12.23/ 21.66 GFLOPS | Progress: (16/20) | 12.31 s
+[Task 13/25] Current/Best: 18.57/ 21.66 GFLOPS | Progress: (20/20) | 14.53 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.60/ 13.60 GFLOPS | Progress: (4/20) | 3.32 s
-[Task 14/25] Current/Best: 6.11/ 13.60 GFLOPS | Progress: (8/20) | 5.49 s
-[Task 14/25] Current/Best: 20.08/ 20.08 GFLOPS | Progress: (12/20) | 8.03 s
-[Task 14/25] Current/Best: 16.19/ 20.08 GFLOPS | Progress: (16/20) | 9.69 s Done.
+[Task 14/25] Current/Best: 13.65/ 13.65 GFLOPS | Progress: (4/20) | 3.28 s
+[Task 14/25] Current/Best: 6.08/ 13.65 GFLOPS | Progress: (8/20) | 5.49 s
+[Task 14/25] Current/Best: 20.77/ 20.77 GFLOPS | Progress: (12/20) | 8.01 s
+[Task 14/25] Current/Best: 16.19/ 20.77 GFLOPS | Progress: (16/20) | 9.65 s Done.
-[Task 14/25] Current/Best: 17.11/ 20.08 GFLOPS | Progress: (20/20) | 11.47 s
+[Task 14/25] Current/Best: 17.20/ 20.77 GFLOPS | Progress: (20/20) | 11.36 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.12/ 17.59 GFLOPS | Progress: (4/20) | 2.77 s
-[Task 15/25] Current/Best: 14.28/ 18.12 GFLOPS | Progress: (8/20) | 4.12 s
-[Task 15/25] Current/Best: 10.39/ 22.28 GFLOPS | Progress: (12/20) | 6.21 s
-[Task 15/25] Current/Best: 20.38/ 22.28 GFLOPS | Progress: (16/20) | 9.16 s
-[Task 15/25] Current/Best: 9.64/ 22.28 GFLOPS | Progress: (20/20) | 10.13 s
+[Task 15/25] Current/Best: 16.20/ 17.63 GFLOPS | Progress: (4/20) | 2.70 s
+[Task 15/25] Current/Best: 14.45/ 18.13 GFLOPS | Progress: (8/20) | 4.03 s
+[Task 15/25] Current/Best: 10.38/ 22.19 GFLOPS | Progress: (12/20) | 6.09 s
+[Task 15/25] Current/Best: 20.40/ 22.19 GFLOPS | Progress: (16/20) | 9.42 s
+[Task 15/25] Current/Best: 9.70/ 22.19 GFLOPS | Progress: (20/20) | 10.44 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.69/ 20.69 GFLOPS | Progress: (4/20) | 3.06 s
-[Task 16/25] Current/Best: 3.04/ 20.69 GFLOPS | Progress: (8/20) | 4.71 s
-[Task 16/25] Current/Best: 19.76/ 20.69 GFLOPS | Progress: (12/20) | 5.93 s
-[Task 16/25] Current/Best: 17.22/ 20.69 GFLOPS | Progress: (16/20) | 7.30 s
-[Task 16/25] Current/Best: 10.12/ 22.27 GFLOPS | Progress: (20/20) | 9.34 s Done.
+[Task 16/25] Current/Best: 20.47/ 20.47 GFLOPS | Progress: (4/20) | 2.97 s
+[Task 16/25] Current/Best: 3.04/ 20.47 GFLOPS | Progress: (8/20) | 4.58 s
+[Task 16/25] Current/Best: 19.58/ 20.47 GFLOPS | Progress: (12/20) | 5.81 s
+[Task 16/25] Current/Best: 18.06/ 20.47 GFLOPS | Progress: (16/20) | 7.15 s
+[Task 16/25] Current/Best: 9.98/ 22.33 GFLOPS | Progress: (20/20) | 9.19 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.42/ 18.84 GFLOPS | Progress: (4/20) | 4.70 s
-[Task 17/25] Current/Best: 14.38/ 23.00 GFLOPS | Progress: (8/20) | 7.48 s
-[Task 17/25] Current/Best: 16.75/ 23.00 GFLOPS | Progress: (12/20) | 9.54 s
-[Task 17/25] Current/Best: 16.44/ 23.00 GFLOPS | Progress: (16/20) | 11.66 s
-[Task 17/25] Current/Best: 10.03/ 23.00 GFLOPS | Progress: (20/20) | 13.80 s Done.
+[Task 17/25] Current/Best: 13.31/ 16.81 GFLOPS | Progress: (4/20) | 4.71 s
+[Task 17/25] Current/Best: 14.39/ 23.25 GFLOPS | Progress: (8/20) | 7.55 s
+[Task 17/25] Current/Best: 16.84/ 23.25 GFLOPS | Progress: (12/20) | 9.60 s
+[Task 17/25] Current/Best: 16.41/ 23.25 GFLOPS | Progress: (16/20) | 11.75 s
+[Task 17/25] Current/Best: 10.02/ 23.25 GFLOPS | Progress: (20/20) | 13.87 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.25/ 17.09 GFLOPS | Progress: (4/20) | 3.74 s
-[Task 18/25] Current/Best: 10.59/ 19.53 GFLOPS | Progress: (8/20) | 7.26 s
-[Task 18/25] Current/Best: 19.27/ 19.53 GFLOPS | Progress: (12/20) | 9.21 s
-[Task 18/25] Current/Best: 10.02/ 19.53 GFLOPS | Progress: (16/20) | 12.83 s
-[Task 18/25] Current/Best: 20.67/ 20.67 GFLOPS | Progress: (20/20) | 14.37 s Done.
+[Task 18/25] Current/Best: 10.99/ 17.85 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 18/25] Current/Best: 10.55/ 17.85 GFLOPS | Progress: (8/20) | 7.22 s
+[Task 18/25] Current/Best: 19.17/ 19.17 GFLOPS | Progress: (12/20) | 9.14 s
+[Task 18/25] Current/Best: 9.95/ 19.17 GFLOPS | Progress: (16/20) | 12.68 s
+[Task 18/25] Current/Best: 20.65/ 20.65 GFLOPS | Progress: (20/20) | 14.20 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.14/ 20.12 GFLOPS | Progress: (4/20) | 6.06 s
-[Task 19/25] Current/Best: 2.60/ 20.12 GFLOPS | Progress: (8/20) | 9.31 s
-[Task 19/25] Current/Best: 19.20/ 20.93 GFLOPS | Progress: (12/20) | 12.07 s
-[Task 19/25] Current/Best: 15.34/ 21.68 GFLOPS | Progress: (16/20) | 14.91 s
-[Task 19/25] Current/Best: 2.70/ 23.45 GFLOPS | Progress: (20/20) | 17.68 s Done.
+[Task 19/25] Current/Best: 7.14/ 20.26 GFLOPS | Progress: (4/20) | 6.10 s
+[Task 19/25] Current/Best: 2.61/ 20.26 GFLOPS | Progress: (8/20) | 9.36 s
+[Task 19/25] Current/Best: 19.71/ 21.86 GFLOPS | Progress: (12/20) | 12.09 s
+[Task 19/25] Current/Best: 15.07/ 22.26 GFLOPS | Progress: (16/20) | 14.91 s
+[Task 19/25] Current/Best: 2.70/ 23.70 GFLOPS | Progress: (20/20) | 17.72 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 8.79/ 14.94 GFLOPS | Progress: (4/20) | 3.34 s Done.
+[Task 20/25] Current/Best: 9.24/ 15.13 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-[Task 20/25] Current/Best: 9.97/ 14.94 GFLOPS | Progress: (8/20) | 6.65 s
-[Task 20/25] Current/Best: 2.32/ 16.65 GFLOPS | Progress: (12/20) | 10.81 s
-[Task 20/25] Current/Best: 12.35/ 16.65 GFLOPS | Progress: (16/20) | 14.38 s
-[Task 20/25] Current/Best: 13.68/ 21.72 GFLOPS | Progress: (20/20) | 16.47 s
+[Task 20/25] Current/Best: 10.40/ 15.13 GFLOPS | Progress: (8/20) | 6.76 s
+[Task 20/25] Current/Best: 2.32/ 16.65 GFLOPS | Progress: (12/20) | 10.61 s
+[Task 20/25] Current/Best: 12.40/ 16.65 GFLOPS | Progress: (16/20) | 14.15 s
+[Task 20/25] Current/Best: 11.53/ 22.15 GFLOPS | Progress: (20/20) | 16.27 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.39/ 17.70 GFLOPS | Progress: (4/20) | 3.25 s
-[Task 21/25] Current/Best: 14.54/ 17.70 GFLOPS | Progress: (8/20) | 4.83 s
-[Task 21/25] Current/Best: 1.61/ 17.70 GFLOPS | Progress: (12/20) | 7.00 s
... 324 lines suppressed ...