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 2022/06/21 19:09:50 UTC
[tvm-site] branch asf-site updated: deploying docs (apache/tvm@9e58af2abe2cbd1305c6067e02c95f68756e8165)
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 390540a43 deploying docs (apache/tvm@9e58af2abe2cbd1305c6067e02c95f68756e8165)
390540a43 is described below
commit 390540a438c43858b921dc4709c8c3bf3531f078
Author: tvm-bot <95...@users.noreply.github.com>
AuthorDate: Tue Jun 21 19:09:45 2022 +0000
deploying docs (apache/tvm@9e58af2abe2cbd1305c6067e02c95f68756e8165)
---
.../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 | 5 +
.../compile_models/sg_execution_times.rst.txt | 22 +-
.../deploy_models/deploy_model_on_android.rst.txt | 2 +-
.../deploy_object_detection_pytorch.rst.txt | 4 +-
.../deploy_models/deploy_prequantized.rst.txt | 6 +-
.../deploy_prequantized_tflite.rst.txt | 4 +-
.../how_to/deploy_models/deploy_quantized.rst.txt | 2 +-
.../deploy_models/deploy_ssd_gluoncv.rst.txt | 4 +-
.../deploy_models/sg_execution_times.rst.txt | 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 | 1856 ++++++++++++++------
.../tune_network_cuda.rst.txt | 2 +-
.../tune_network_x86.rst.txt | 4 +-
.../tune_sparse_x86.rst.txt | 33 +-
.../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 | 14 +-
.../how_to/work_with_schedules/tensorize.rst.txt | 2 +-
.../tutorials/autotvm/sg_execution_times.rst.txt | 4 +-
.../frontend/deploy_classification.rst.txt | 2 +-
.../tutorials/frontend/deploy_detection.rst.txt | 2 +-
.../tutorials/frontend/sg_execution_times.rst.txt | 6 +-
.../tutorials/optimize/sg_execution_times.rst.txt | 6 +-
.../topic/vta/tutorials/sg_execution_times.rst.txt | 6 +-
.../tutorial/auto_scheduler_matmul_x86.rst.txt | 9 +-
docs/_sources/tutorial/autotvm_matmul_x86.rst.txt | 20 +-
docs/_sources/tutorial/autotvm_relay_x86.rst.txt | 54 +-
.../tutorial/cross_compilation_and_rpc.rst.txt | 2 +-
docs/_sources/tutorial/intro_topi.rst.txt | 2 +-
docs/_sources/tutorial/sg_execution_times.rst.txt | 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 | 145 +-
docs/how_to/compile_models/from_paddle.html | 2 +-
docs/how_to/compile_models/from_pytorch.html | 5 +-
docs/how_to/compile_models/from_tensorflow.html | 1 +
docs/how_to/compile_models/sg_execution_times.html | 32 +-
.../deploy_models/deploy_model_on_android.html | 2 +-
.../deploy_object_detection_pytorch.html | 117 +-
docs/how_to/deploy_models/deploy_prequantized.html | 10 +-
.../deploy_models/deploy_prequantized_tflite.html | 4 +-
docs/how_to/deploy_models/deploy_quantized.html | 2 +-
docs/how_to/deploy_models/deploy_ssd_gluoncv.html | 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 | 1852 +++++++++++++------
.../tune_with_autoscheduler/tune_network_cuda.html | 2 +-
.../tune_with_autoscheduler/tune_network_x86.html | 4 +-
.../tune_with_autoscheduler/tune_sparse_x86.html | 33 +-
.../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 | 14 +-
docs/how_to/work_with_schedules/tensorize.html | 2 +-
docs/reference/api/python/auto_scheduler.html | 4 +-
.../api/typedoc/classes/bytestreamreader.html | 12 +-
.../api/typedoc/classes/cachedcallstack.html | 34 +-
docs/reference/api/typedoc/classes/dldatatype.html | 12 +-
docs/reference/api/typedoc/classes/dldevice.html | 10 +-
.../reference/api/typedoc/classes/environment.html | 12 +-
docs/reference/api/typedoc/classes/ffilibrary.html | 20 +-
.../api/typedoc/classes/graphexecutor.html | 16 +-
docs/reference/api/typedoc/classes/instance.html | 40 +-
docs/reference/api/typedoc/classes/memory.html | 34 +-
docs/reference/api/typedoc/classes/module.html | 10 +-
docs/reference/api/typedoc/classes/ndarray.html | 22 +-
.../api/typedoc/classes/packedfunccell.html | 6 +-
docs/reference/api/typedoc/classes/rpcserver.html | 14 +-
docs/reference/api/typedoc/classes/scalar.html | 6 +-
.../api/typedoc/classes/webgpucontext.html | 12 +-
docs/reference/api/typedoc/enums/argtypecode.html | 30 +-
.../api/typedoc/enums/aynccallbackcode.html | 4 +-
.../api/typedoc/enums/dldatatypecode.html | 8 +-
.../api/typedoc/enums/rpcserverstate.html | 12 +-
docs/reference/api/typedoc/enums/sizeof.html | 18 +-
docs/reference/api/typedoc/index.html | 112 +-
.../api/typedoc/interfaces/disposable.html | 2 +-
.../api/typedoc/interfaces/functioninfo.html | 6 +-
.../api/typedoc/interfaces/libraryprovider.html | 4 +-
docs/searchindex.js | 2 +-
.../vta/tutorials/autotvm/sg_execution_times.html | 4 +-
.../tutorials/frontend/deploy_classification.html | 2 +-
.../vta/tutorials/frontend/deploy_detection.html | 2 +-
.../vta/tutorials/frontend/sg_execution_times.html | 6 +-
.../vta/tutorials/optimize/sg_execution_times.html | 6 +-
docs/topic/vta/tutorials/sg_execution_times.html | 6 +-
docs/tutorial/auto_scheduler_matmul_x86.html | 5 +-
docs/tutorial/autotvm_matmul_x86.html | 20 +-
docs/tutorial/autotvm_relay_x86.html | 258 +--
docs/tutorial/cross_compilation_and_rpc.html | 2 +-
docs/tutorial/intro_topi.html | 2 +-
docs/tutorial/sg_execution_times.html | 26 +-
docs/tutorial/tensor_expr_get_started.html | 43 +-
121 files changed, 3558 insertions(+), 2045 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 f09c930dd..0a66b58e9 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.zip7c678cb0-de9e-43d6-a903-ae5d0831a9f1 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/resnet18_v1-a0666292.zip...
+ Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip8471296b-714d-4d7b-8c25-e1543c5e83fe 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 baa3ae1db..16b7bf95e 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<07:46, 93.2kB/s]
0%| | 48.0k/41.5M [00:00<04:54, 147kB/s]
0%| | 104k/41.5M [00:00<03:10, 228kB/s]
1%| | 216k/41.5M [00:00<01:49, 394kB/s]
1%|1 | 432k/41.5M [00:00<01:01, 703kB/s]
2%|1 | 712k/41.5M [00:01<00:42, 1.02MB/s]
2%|2 | 0.98M/41.5M [00:01<00:34, 1.23MB/s]
3%|3 | 1.27M/41.5M [00:01<00:30, 1.38MB/s]
4%|3 | 1.58M/41.5M [00:01<00:27, 1.53MB/s]
5%|4 | 1.90M/41.5M [00:01<00:25, 1.64MB/s]
5%|5 | 2.24M/41.5M [00:01<00:23, 1.76MB/s]
6%|6 | 2.60M/41.5M [00:02<00:21, 1.87MB/s]
7%|7 | 2.98M/41.5M [00:02<00:20, 1.98MB/s]
8%|8 | 3.38M/41.5M [00:02<00:19, 2.09MB/s]
9%|9 | 3.78M/41.5M [00:02<00:18, 2.19MB/s]
10%|# | 4.22M/41.5M [00:02<00:16, 2.31MB/s]
11%|#1 | 4.67M/41.5M [00:03<00
:15, 2.42MB/s]
12%|#2 | 5.15M/41.5M [00:03<00:14, 2.54MB/s]
14%|#3 | 5.66M/41.5M [00:03<00:13, 2.68MB/s]
15%|#4 | 6.19M/41.5M [00:03<00:13, 2.82MB/s]
16%|#6 | 6.73M/41.5M [00:03<00:12, 2.95MB/s]
18%|#7 | 7.32M/41.5M [00:03<00:11, 3.10MB/s]
19%|#9 | 7.93M/41.5M [00:04<00:10, 3.26MB/s]
21%|## | 8.57M/41.5M [00:04<00:10, 3.42MB/s]
22%|##2 | 9.24M/41.5M [00:04<00:08, 4.11MB/s]
23%|##3 | 9.67M/41.5M [00:04<00:08, 4.07MB/s]
24%|##4 | 10.1M/41.5M [00:04<00:08, 3.79MB/s]
26%|##5 | 10.7M/41.5M [00:04<00:07, 4.37MB/s]
27%|##6 | 11.2M/41.5M [00:04<00:07, 4.36MB/s]
28%|##7 | 11.6M/41.5M [00:04<00:07, 4.01MB/s]
30%|##9 | 12.3M/41.5M [00:05<00:06, 4.78MB/s]
31%|### | 12.8M/41.5M [00:05<00:06, 4.81MB/s]
32%|###2 | 13.3M/41.5M [00:05<00:06, 4.42MB/s]
34%|###3 | 14.0M/41.5M [00:05<00:05, 5.27MB/s]
35%|###5
| 14.6M/41.5M [00:05<00:05, 5.29MB/s]
36%|###6 | 15.1M/41.5M [00:05<00:05, 4.81MB/s]
39%|###8 | 16.0M/41.5M [00:05<00:04, 5.79MB/s]
40%|###9 | 16.6M/41.5M [00:05<00:04, 5.84MB/s]
41%|####1 | 17.2M/41.5M [00:06<00:04, 5.31MB/s]
44%|####3 | 18.1M/41.5M [00:06<00:03, 6.42MB/s]
45%|####5 | 18.8M/41.5M [00:06<00:03, 6.47MB/s]
47%|####6 | 19.4M/41.5M [00:06<00:03, 5.87MB/s]
49%|####9 | 20.5M/41.5M [00:06<00:03, 5.99MB/s]
52%|#####2 | 21.7M/41.5M [00:06<00:03, 6.52MB/s]
56%|#####5 | 23.1M/41.5M [00:06<00:02, 6.97MB/s]
59%|#####8 | 24.5M/41.5M [00:07<00:02, 7.40MB/s]
62%|######2 | 25.9M/41.5M [00:07<00:02, 7.82MB/s]
66%|######6 | 27.4M/41.5M [00:07<00:01, 8.11MB/s]
70%|######9 | 28.9M/41.5M [00:07<00:01, 8.28MB/s]
73%|#######3 | 30.3M/41.5M [00:07<00:01, 8.42MB/s]
77%|#######6 | 31.8M/41.5M [00:07<00:01, 8.51MB/s]
80%|######## | 33.3M/41.5M [00:08<0
0:01, 8.58MB/s]
84%|########3 | 34.8M/41.5M [00:08<00:00, 8.62MB/s]
87%|########7 | 36.2M/41.5M [00:08<00:00, 8.66MB/s]
91%|######### | 37.7M/41.5M [00:08<00:00, 9.88MB/s]
93%|#########3| 38.7M/41.5M [00:08<00:00, 9.81MB/s]
96%|#########5| 39.7M/41.5M [00:08<00:00, 8.99MB/s]
98%|#########7| 40.7M/41.5M [00:09<00:00, 7.94MB/s]
100%|##########| 41.5M/41.5M [00:09<00:00, 4.81MB/s]
+
0%| | 0.00/41.5M [00:00<?, ?B/s]
0%| | 16.0k/41.5M [00:00<07:48, 92.8kB/s]
0%| | 48.0k/41.5M [00:00<04:55, 147kB/s]
0%| | 80.0k/41.5M [00:00<04:24, 164kB/s]
0%| | 136k/41.5M [00:00<03:10, 227kB/s]
1%| | 232k/41.5M [00:00<02:05, 346kB/s]
1%| | 336k/41.5M [00:01<01:39, 432kB/s]
1%|1 | 440k/41.5M [00:01<01:28, 487kB/s]
1%|1 | 544k/41.5M [00:01<01:22, 524kB/s]
2%|1 | 664k/41.5M [00:01<01:14, 577kB/s]
2%|1 | 784k/41.5M [00:01<01:09, 613kB/s]
2%|2 | 904k/41.5M [00:01<01:06, 638kB/s]
2%|2 | 1.02M/41.5M [00:02<01:02, 683kB/s]
3%|2 | 1.15M/41.5M [00:02<00:59, 714kB/s]
3%|3 | 1.30M/41.5M [00:02<00:55, 764kB/s]
3%|3 | 1.45M/41.5M [00:02<00:52, 798kB/s]
4%|3 | 1.60M/41.5M [00:02<00:49, 837kB/s]
4%|4 | 1.77M/41.5M [00:03<00:47, 877kB/s]
5%|4 | 1.95M/41.5M [00:03<00:44, 933kB/s]
5%|5 | 2.12M/41.5M [00:03<00:42, 972kB/s]
6%|5 | 2.31M/41.5M [00:03<00:40, 1.01MB/s]
6%|6 | 2.52M/41.5M [00:03<00:38, 1.07MB/s]
7%|6 | 2.72M/41.5M [00:03<00:36, 1.11MB/s]
7%|7 | 2.93M/41.5M [00:04<00:35, 1.15MB/s]
8%|7 | 3.15M/41.5M [00:04<00:33, 1.19MB/s]
8%|8 | 3.38M/41.5M [00:04<00:31, 1.25MB/s]
9%|8 | 3.62M/41.5M [00:04<00:30, 1.31MB/s]
9%|9 | 3.88M/41.5M [00:04<00:28, 1.37MB/s]
10%|9 | 4.15M/41.5M [00:04<00:27, 1.43MB/s]
11%|# | 4.43M/41.5M [00:05<00:25, 1.50MB/s]
11%|#1 | 4.73M/41.5M [00:05<00:24, 1.58MB/s]
12%|#2 | 5.03M/41.5M [00:05<00:23, 1.65MB/s]
13%|#2 | 5.35M/41.5M [00:05<00:20, 1.85MB/s]
14%|#3 | 5.69M/41.5M [00:05<00:18, 2.08MB/s]
15%|#4 | 6.04M/41.5M [00:05<00:16, 2.25MB/s]
15%|#5 | 6.27M/41.5
M [00:06<00:17, 2.11MB/s]
16%|#5 | 6.48M/41.5M [00:06<00:20, 1.82MB/s]
16%|#6 | 6.80M/41.5M [00:06<00:19, 1.85MB/s]
17%|#7 | 7.19M/41.5M [00:06<00:17, 2.00MB/s]
18%|#8 | 7.59M/41.5M [00:06<00:16, 2.13MB/s]
19%|#9 | 8.01M/41.5M [00:06<00:15, 2.23MB/s]
20%|## | 8.45M/41.5M [00:07<00:14, 2.34MB/s]
21%|##1 | 8.90M/41.5M [00:07<00:12, 2.66MB/s]
23%|##2 | 9.35M/41.5M [00:07<00:11, 2.90MB/s]
24%|##3 | 9.81M/41.5M [00:07<00:10, 3.13MB/s]
24%|##4 | 10.1M/41.5M [00:07<00:11, 2.87MB/s]
25%|##5 | 10.4M/41.5M [00:07<00:13, 2.47MB/s]
26%|##6 | 10.9M/41.5M [00:07<00:11, 2.80MB/s]
27%|##7 | 11.4M/41.5M [00:08<00:09, 3.21MB/s]
28%|##8 | 11.7M/41.5M [00:08<00:09, 3.32MB/s]
29%|##9 | 12.1M/41.5M [00:08<00:10, 2.83MB/s]
30%|### | 12.6M/41.5M [00:08<00:09, 3.17MB/s]
32%|###1 | 13.2M/41.5M [00:08<00:08, 3.65MB/s]
33%|###2 | 13.6M/41.5M [00:08<00:07, 3.76MB/s]
34%|###3 | 13.9M/41.5M [00:08<00:09, 3.20MB/s]
35%|###4 | 14.5M/41.5M [00:08<00:07, 3.57MB/s]
36%|###6 | 15.1M/41.5M [00:09<00:06, 4.29MB/s]
38%|###7 | 15.6M/41.5M [00:09<00:06, 4.11MB/s]
39%|###8 | 16.0M/41.5M [00:09<00:07, 3.52MB/s]
40%|#### | 16.6M/41.5M [00:09<00:06, 4.03MB/s]
42%|####1 | 17.4M/41.5M [00:09<00:05, 4.89MB/s]
43%|####3 | 17.9M/41.5M [00:09<00:05, 4.68MB/s]
44%|####4 | 18.4M/41.5M [00:09<00:06, 4.01MB/s]
46%|####6 | 19.1M/41.5M [00:10<00:05, 4.62MB/s]
48%|####8 | 20.0M/41.5M [00:10<00:04, 5.64MB/s]
50%|####9 | 20.6M/41.5M [00:10<00:04, 5.38MB/s]
51%|##### | 21.1M/41.5M [00:10<00:04, 4.60MB/s]
53%|#####2 | 22.0M/41.5M [00:10<00:03, 5.31MB/s]
55%|#####5 | 23.0M/41.5M [00:10<00:02, 6.50MB/s]
57%|#####6 | 23.6M/41.5M [00:10<00:03, 6.18MB/s]
58%|#####8 | 24.3M/41.
5M [00:10<00:03, 5.31MB/s]
61%|###### | 25.2M/41.5M [00:11<00:02, 6.09MB/s]
64%|######3 | 26.4M/41.5M [00:11<00:02, 7.40MB/s]
65%|######5 | 27.1M/41.5M [00:11<00:02, 7.03MB/s]
67%|######7 | 27.9M/41.5M [00:11<00:02, 6.05MB/s]
70%|######9 | 28.9M/41.5M [00:11<00:01, 6.86MB/s]
73%|#######2 | 30.1M/41.5M [00:11<00:01, 8.26MB/s]
75%|#######4 | 31.0M/41.5M [00:11<00:01, 7.72MB/s]
77%|#######6 | 31.8M/41.5M [00:12<00:01, 6.66MB/s]
79%|#######9 | 33.0M/41.5M [00:12<00:01, 6.90MB/s]
83%|########2 | 34.4M/41.5M [00:12<00:00, 7.49MB/s]
87%|########6 | 35.9M/41.5M [00:12<00:00, 7.88MB/s]
90%|######### | 37.4M/41.5M [00:12<00:00, 9.39MB/s]
93%|#########3| 38.7M/41.5M [00:12<00:00, 10.3MB/s]
96%|#########5| 39.8M/41.5M [00:12<00:00, 9.13MB/s]
98%|#########8| 40.7M/41.5M [00:13<00:00, 7.96MB/s]
100%|##########| 41.5M/41.5M [00:13<00:00, 3.32MB/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 e87116030..3f3682878 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 6.300 seconds)
+ **Total running time of the script:** ( 1 minutes 16.093 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 3b33d1dd1..26005aaf7 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]
45%|####5 | 20.2M/44.7M [00:00<00:00, 211MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 244MB/s]
+
0%| | 0.00/44.7M [00:00<?, ?B/s]
29%|##8 | 12.7M/44.7M [00:00<00:00, 134MB/s]
71%|#######1 | 31.8M/44.7M [00:00<00:00, 172MB/s]
100%|##########| 44.7M/44.7M [00:00<00:00, 175MB/s]
diff --git a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
index e6f3342e0..3c8a27a0c 100644
--- a/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
+++ b/docs/_sources/how_to/compile_models/from_tensorflow.rst.txt
@@ -420,6 +420,11 @@ Run the corresponding model on tensorflow
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 2.200 seconds)
+
+
.. _sphx_glr_download_how_to_compile_models_from_tensorflow.py:
.. only:: html
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 6a782c370..01fb9c4a9 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
=================
-**05:17.291** total execution time for **how_to_compile_models** files:
+**06:02.276** total execution time for **how_to_compile_models** files:
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:06.300 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_paddle.py` (``from_paddle.py``) | 01:16.093 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 00:59.282 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tensorflow.py` (``from_tensorflow.py``) | 01:02.200 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:55.408 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_darknet.py` (``from_darknet.py``) | 00:58.148 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:34.374 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_oneflow.py` (``from_oneflow.py``) | 00:38.774 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.654 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:37.609 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.174 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_tflite.py` (``from_tflite.py``) | 00:23.928 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.239 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_mxnet.py` (``from_mxnet.py``) | 00:22.722 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.242 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_coreml.py` (``from_coreml.py``) | 00:21.724 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_keras.py` (``from_keras.py``) | 00:14.406 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_pytorch.py` (``from_pytorch.py``) | 00:18.671 | 0.0 MB |
+-----------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.214 | 0.0 MB |
+| :ref:`sphx_glr_how_to_compile_models_from_onnx.py` (``from_onnx.py``) | 00:02.407 | 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 fe1122442..54d3a1d9c 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)
- 15.8870 15.8812 16.0615 15.7296 0.0960
+ 15.9824 16.0376 16.1860 15.7171 0.1692
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 f71eaae04..1d8af0591 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]
1%| | 1.12M/170M [00:00<00:15, 11.5MB/s]
2%|2 | 3.44M/170M [00:00<00:09, 18.7MB/s]
4%|3 | 6.12M/170M [00:00<00:07, 22.9MB/s]
5%|4 | 8.32M/170M [00:00<00:07, 22.7MB/s]
6%|6 | 10.5M/170M [00:00<00:07, 21.7MB/s]
9%|8 | 14.4M/170M [00:00<00:05, 28.1MB/s]
10%|# | 17.3M/170M [00:00<00:05, 27.0MB/s]
12%|#1 | 19.9M/170M [00:00<00:06, 25.9MB/s]
14%|#3 | 23.7M/170M [00:00<00:05, 29.8MB/s]
16%|#6 | 27.4M/170M [00:01<00:04, 32.5MB/s]
18%|#8 | 30.6M/170M [00:01<00:05, 28.1MB/s]
20%|#9 | 33.4M/170M [00:01<00:05, 27.1MB/s]
21%|##1 | 36.1M/170M [00:01<00:05, 25.1MB/s]
23%|##2 | 38.5M/170M [00:01<00:05, 23.2MB/s]
24%|##4 | 41.2M/170M [00:01<00:05, 24.3MB/s]
26%|##5 | 43.6M/170M [00:01<00:06, 20.8MB/s]
28%|##7 | 47.1M/170M [00:01<00:05, 24.6MB/
s]
31%|###1 | 52.9M/170M [00:02<00:03, 34.0MB/s]
33%|###3 | 56.5M/170M [00:02<00:03, 35.0MB/s]
35%|###5 | 60.0M/170M [00:02<00:03, 29.3MB/s]
37%|###7 | 63.1M/170M [00:02<00:04, 27.2MB/s]
39%|###9 | 66.9M/170M [00:02<00:03, 30.3MB/s]
42%|####2 | 71.6M/170M [00:02<00:02, 34.7MB/s]
44%|####4 | 75.5M/170M [00:02<00:02, 36.3MB/s]
47%|####6 | 79.1M/170M [00:02<00:02, 32.0MB/s]
50%|####9 | 84.3M/170M [00:03<00:02, 37.6MB/s]
52%|#####1 | 88.1M/170M [00:03<00:02, 30.8MB/s]
54%|#####3 | 91.4M/170M [00:03<00:03, 26.9MB/s]
55%|#####5 | 94.2M/170M [00:03<00:03, 25.9MB/s]
58%|#####7 | 98.5M/170M [00:03<00:02, 30.0MB/s]
60%|#####9 | 102M/170M [00:03<00:02, 28.2MB/s]
62%|######1 | 105M/170M [00:03<00:02, 29.5MB/s]
63%|######3 | 108M/170M [00:04<00:02, 27.0MB/s]
65%|######5 | 110M/170M [00:04<00:02, 25.3MB/s]
67%|######6 | 113M/170M [00:04<00:02,
25.1MB/s]
68%|######8 | 116M/170M [00:04<00:02, 26.2MB/s]
70%|######9 | 119M/170M [00:04<00:02, 26.2MB/s]
71%|#######1 | 121M/170M [00:04<00:02, 24.8MB/s]
74%|#######4 | 126M/170M [00:04<00:01, 32.5MB/s]
77%|#######6 | 130M/170M [00:04<00:01, 34.2MB/s]
80%|#######9 | 135M/170M [00:04<00:00, 39.6MB/s]
82%|########1 | 139M/170M [00:05<00:00, 39.3MB/s]
85%|########4 | 144M/170M [00:05<00:00, 41.9MB/s]
87%|########6 | 148M/170M [00:05<00:00, 32.4MB/s]
89%|########8 | 151M/170M [00:05<00:00, 31.2MB/s]
92%|#########1| 156M/170M [00:05<00:00, 36.3MB/s]
94%|#########4| 160M/170M [00:05<00:00, 37.7MB/s]
97%|#########7| 165M/170M [00:05<00:00, 41.1MB/s]
99%|#########9| 169M/170M [00:05<00:00, 41.4MB/s]
100%|##########| 170M/170M [00:05<00:00, 30.4MB/s]
+
0%| | 0.00/170M [00:00<?, ?B/s]
2%|1 | 2.94M/170M [00:00<00:06, 25.2MB/s]
3%|3 | 5.65M/170M [00:00<00:07, 23.5MB/s]
5%|4 | 8.15M/170M [00:00<00:06, 24.3MB/s]
6%|6 | 10.6M/170M [00:00<00:06, 24.6MB/s]
8%|7 | 13.6M/170M [00:00<00:06, 24.4MB/s]
9%|9 | 15.9M/170M [00:00<00:07, 22.5MB/s]
11%|#1 | 19.0M/170M [00:00<00:06, 25.2MB/s]
13%|#2 | 21.6M/170M [00:00<00:06, 25.5MB/s]
14%|#4 | 24.4M/170M [00:01<00:05, 26.6MB/s]
17%|#6 | 28.4M/170M [00:01<00:05, 28.0MB/s]
18%|#8 | 31.1M/170M [00:01<00:05, 27.0MB/s]
20%|#9 | 33.7M/170M [00:01<00:05, 26.2MB/s]
21%|##1 | 36.5M/170M [00:01<00:05, 27.0MB/s]
23%|##3 | 39.1M/170M [00:01<00:05, 25.6MB/s]
25%|##5 | 42.5M/170M [00:01<00:04, 28.2MB/s]
27%|##6 | 45.3M/170M [00:01<00:04, 28.3MB/s]
28%|##8 | 48.0M/170M [00:01<00:05, 23.6MB/
s]
30%|##9 | 50.7M/170M [00:02<00:05, 24.7MB/s]
32%|###2 | 54.8M/170M [00:02<00:04, 29.0MB/s]
34%|###3 | 57.6M/170M [00:02<00:04, 28.8MB/s]
36%|###5 | 60.9M/170M [00:02<00:03, 30.1MB/s]
38%|###8 | 64.9M/170M [00:02<00:03, 33.4MB/s]
40%|#### | 68.2M/170M [00:02<00:04, 22.6MB/s]
42%|####2 | 71.5M/170M [00:02<00:04, 25.3MB/s]
44%|####3 | 74.4M/170M [00:02<00:04, 24.8MB/s]
45%|####5 | 77.2M/170M [00:03<00:03, 25.9MB/s]
48%|####7 | 81.1M/170M [00:03<00:03, 29.7MB/s]
50%|####9 | 84.5M/170M [00:03<00:02, 31.3MB/s]
52%|#####1 | 87.7M/170M [00:03<00:03, 27.7MB/s]
53%|#####3 | 90.5M/170M [00:03<00:03, 23.8MB/s]
55%|#####4 | 93.0M/170M [00:03<00:03, 21.8MB/s]
56%|#####6 | 95.2M/170M [00:03<00:03, 21.1MB/s]
57%|#####7 | 97.3M/170M [00:04<00:03, 20.4MB/s]
58%|#####8 | 99.3M/170M [00:04<00:03, 20.0MB/s]
60%|#####9 | 102M/170M [00:04<00:0
3, 20.8MB/s]
61%|###### | 104M/170M [00:04<00:03, 20.3MB/s]
62%|######2 | 106M/170M [00:04<00:03, 20.3MB/s]
63%|######3 | 108M/170M [00:04<00:03, 18.2MB/s]
65%|######4 | 110M/170M [00:04<00:03, 19.9MB/s]
66%|######6 | 113M/170M [00:04<00:02, 22.0MB/s]
68%|######7 | 115M/170M [00:04<00:02, 22.9MB/s]
69%|######9 | 118M/170M [00:04<00:02, 23.8MB/s]
71%|####### | 120M/170M [00:05<00:03, 17.3MB/s]
72%|#######1 | 122M/170M [00:05<00:03, 15.4MB/s]
73%|#######2 | 124M/170M [00:05<00:03, 16.0MB/s]
74%|#######3 | 125M/170M [00:05<00:03, 15.5MB/s]
75%|#######4 | 127M/170M [00:05<00:02, 16.3MB/s]
76%|#######6 | 130M/170M [00:05<00:02, 19.1MB/s]
78%|#######7 | 132M/170M [00:05<00:01, 20.1MB/s]
79%|#######9 | 134M/170M [00:06<00:01, 20.6MB/s]
81%|######## | 137M/170M [00:06<00:01, 23.1MB/s]
83%|########3 | 141M/170M [00:06<00:01, 27.7MB/s]
85%|########5 | 144M/170M [00:06<00:00, 29.
1MB/s]
87%|########6 | 147M/170M [00:06<00:00, 26.2MB/s]
88%|########8 | 150M/170M [00:06<00:00, 21.7MB/s]
90%|########9 | 152M/170M [00:06<00:00, 21.8MB/s]
91%|######### | 154M/170M [00:06<00:00, 21.2MB/s]
92%|#########2| 157M/170M [00:07<00:00, 22.8MB/s]
94%|#########3| 159M/170M [00:07<00:00, 21.7MB/s]
95%|#########4| 161M/170M [00:07<00:00, 17.9MB/s]
96%|#########6| 163M/170M [00:07<00:00, 16.6MB/s]
97%|#########7| 165M/170M [00:07<00:00, 17.8MB/s]
98%|#########8| 167M/170M [00:07<00:00, 17.4MB/s]
100%|#########9| 169M/170M [00:07<00:00, 19.0MB/s]
100%|##########| 170M/170M [00:07<00:00, 22.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -291,7 +291,7 @@ Get boxes with score larger than 0.9
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 58.922 seconds)
+ **Total running time of the script:** ( 3 minutes 2.363 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 8b79527ba..8dff2de80 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]
25%|##5 | 3.44M/13.6M [00:00<00:00, 35.6MB/s]
59%|#####9 | 8.01M/13.6M [00:00<00:00, 42.8MB/s]
98%|#########7| 13.3M/13.6M [00:00<00:00, 48.3MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 46.7MB/s]
+
0%| | 0.00/13.6M [00:00<?, ?B/s]
63%|######3 | 8.56M/13.6M [00:00<00:00, 89.8MB/s]
100%|##########| 13.6M/13.6M [00:00<00:00, 107MB/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)
- 90.2597 90.2117 91.6938 90.0894 0.2076
+ 90.6415 90.5647 93.9084 90.2142 0.4663
@@ -448,7 +448,7 @@ TODO
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 6.321 seconds)
+ **Total running time of the script:** ( 1 minutes 7.363 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 8ee4d6872..15b4f97a1 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)
- 118.8775 118.7901 120.1228 118.3676 0.3213
+ 120.8385 120.7629 122.8763 120.1450 0.4634
@@ -463,7 +463,7 @@ Here we give an example of how to measure performance of TVM compiled models.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 52.980 seconds)
+ **Total running time of the script:** ( 1 minutes 54.209 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 2b05640e1..85e41c9f4 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 12.239 seconds)
+ **Total running time of the script:** ( 1 minutes 14.848 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 22bdbbc72..103d8823d 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%|5 | 6973/132723 [00:00<00:01, 69713.78KB/s]
12%|#1 | 15733/132723 [00:00<00:01, 80225.91KB/s]
18%|#8 | 24531/132723 [00:00<00:01, 83761.96KB/s]
25%|##4 | 32908/132723 [00:00<00:01, 74940.47KB/s]
31%|###1 | 41510/132723 [00:00<00:01, 78654.23KB/s]
38%|###7 | 50255/132723 [00:00<00:01, 81498.05KB/s]
45%|####4 | 59069/132723 [00:00<00:00, 83597.40KB/s]
51%|#####1 | 67801/132723 [00:00<00:00, 84754.52KB/s]
58%|#####7 | 76642/132723 [00:00<00:00, 85870.72KB/s]
64%|######4 | 85434/132723 [00:01<00:00, 86494.22KB/s]
71%|####### | 94197/132723 [00:01<00:00, 86836.33KB/s]
78%|#######7 | 102965/132723 [00:01<00:00, 87087.75KB/s]
84%|########4 | 111745/132723 [00:01<00:00, 87297.65KB/s]
91%|######### | 120484/132723 [00:01<00:00, 87288.26KB/s]
97%|#########7| 129354/132723 [00:01<00:00, 87704.11KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84515.06KB/s]
+
0%| | 0/132723 [00:00<?, ?KB/s]
4%|4 | 5752/132723 [00:00<00:02, 57511.83KB/s]
11%|# | 14438/132723 [00:00<00:01, 74770.40KB/s]
17%|#7 | 23085/132723 [00:00<00:01, 80107.77KB/s]
24%|##3 | 31776/132723 [00:00<00:01, 82789.62KB/s]
30%|### | 40277/132723 [00:00<00:01, 83577.78KB/s]
37%|###6 | 48910/132723 [00:00<00:00, 84510.00KB/s]
43%|####3 | 57575/132723 [00:00<00:00, 85207.36KB/s]
50%|####9 | 66323/132723 [00:00<00:00, 85929.18KB/s]
56%|#####6 | 74971/132723 [00:00<00:00, 86099.34KB/s]
63%|######3 | 83688/132723 [00:01<00:00, 86427.33KB/s]
70%|######9 | 92421/132723 [00:01<00:00, 86701.51KB/s]
76%|#######6 | 101095/132723 [00:01<00:00, 86710.41KB/s]
83%|########2 | 109767/132723 [00:01<00:00, 86476.08KB/s]
89%|########9 | 118444/132723 [00:01<00:00, 86562.60KB/s]
96%|#########5| 127106/132723 [00:01<00:00, 86578.66KB/s]
100%|#######
###| 132723/132723 [00:01<00:00, 84697.10KB/s]
@@ -240,7 +240,7 @@ Display result
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 2 minutes 17.561 seconds)
+ **Total running time of the script:** ( 2 minutes 19.340 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 f49456b6b..904369aa1 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
=================
-**10:17.402** total execution time for **how_to_deploy_models** files:
+**10:28.147** total execution time for **how_to_deploy_models** files:
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 02:58.922 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_object_detection_pytorch.py` (``deploy_object_detection_pytorch.py``) | 03:02.363 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:17.561 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_ssd_gluoncv.py` (``deploy_ssd_gluoncv.py``) | 02:19.340 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:52.980 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized_tflite.py` (``deploy_prequantized_tflite.py``) | 01:54.209 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:12.239 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_quantized.py` (``deploy_quantized.py``) | 01:14.848 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:06.321 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_prequantized.py` (``deploy_prequantized.py``) | 01:07.363 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:27.917 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_android.py` (``deploy_model_on_android.py``) | 00:28.312 | 0.0 MB |
+------------------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.456 | 0.0 MB |
+| :ref:`sphx_glr_how_to_deploy_models_deploy_model_on_rasp.py` (``deploy_model_on_rasp.py``) | 00:21.707 | 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 cae1a2b4a..12dbf952d 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.zipc0ce8fef-9889-4a91-a65b-f0fd93e25599 from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/mobilenet0.25-9f83e440.zip...
+ Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zip6649b730-1211-4ad2-b2c4-4c615777e39e 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 d8f523215..343c1c1eb 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
=================
-**00:39.337** total execution time for **how_to_extend_tvm** files:
+**00:40.567** 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``) | 00:36.224 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_bring_your_own_datatypes.py` (``bring_your_own_datatypes.py``) | 00:37.292 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.194 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_instrument.py` (``use_pass_instrument.py``) | 00:02.320 | 0.0 MB |
+-------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.913 | 0.0 MB |
+| :ref:`sphx_glr_how_to_extend_tvm_use_pass_infra.py` (``use_pass_infra.py``) | 00:00.948 | 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 f75e9c6fb..9ceaedd60 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: 6844us [6844us] (45.78%; 45.78%)
- FoldScaleAxis: 8106us [6us] (54.22%; 54.22%)
- FoldConstant: 8100us [1620us] (54.18%; 99.93%)
- InferType: 6480us [6480us] (43.34%; 80.00%)
+ InferType: 7056us [7056us] (45.72%; 45.72%)
+ FoldScaleAxis: 8379us [6us] (54.28%; 54.28%)
+ FoldConstant: 8373us [1625us] (54.24%; 99.93%)
+ InferType: 6748us [6748us] (43.72%; 80.60%)
@@ -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: 6564us [6564us] (44.86%; 44.86%)
- FoldScaleAxis: 8070us [5us] (55.14%; 55.14%)
- FoldConstant: 8065us [1632us] (55.11%; 99.94%)
- InferType: 6432us [6432us] (43.96%; 79.76%)
+ InferType: 6822us [6822us] (45.19%; 45.19%)
+ FoldScaleAxis: 8273us [7us] (54.81%; 54.81%)
+ FoldConstant: 8266us [1667us] (54.76%; 99.92%)
+ InferType: 6599us [6599us] (43.72%; 79.83%)
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 3fcd76a6f..00767338e 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: 51.593448 ms
+ Convolution: 54.169477 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 697261b0b..1e12fcfbb 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: 9.858491 ms
+ conv2d with tensor core: 8.177830 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 86223a551..cb3ed3d09 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: 0.018503
- Baseline: 3.387383
+ Numpy running time: 0.019089
+ Baseline: 3.440015
@@ -226,7 +226,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
.. code-block:: none
- Opt1: 0.303339
+ Opt1: 0.294212
@@ -329,7 +329,7 @@ In this tutorial, we chose to vectorize the inner loop row data since it is cach
.. code-block:: none
- Opt2: 0.337359
+ Opt2: 0.332334
@@ -425,7 +425,7 @@ the access pattern for A matrix is more cache friendly.
.. code-block:: none
- Opt3: 0.118771
+ Opt3: 0.118769
@@ -550,7 +550,7 @@ flattening.
.. code-block:: none
- Opt4: 0.112118
+ Opt4: 0.110636
@@ -672,7 +672,7 @@ write to C when all the block results are ready.
.. code-block:: none
- Opt5: 0.111604
+ Opt5: 0.111732
@@ -797,7 +797,7 @@ Futhermore, we can also utilize multi-core processors to do the thread-level par
.. code-block:: none
- Opt6: 0.145054
+ Opt6: 0.145305
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 52c77dacd..b17d0f6e4 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
=================
-**00:34.318** total execution time for **how_to_optimize_operators** files:
+**00:34.534** total execution time for **how_to_optimize_operators** files:
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.088 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_gemm.py` (``opt_gemm.py``) | 00:32.231 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.245 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_tensorcore.py` (``opt_conv_tensorcore.py``) | 00:01.260 | 0.0 MB |
+-----------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:00.984 | 0.0 MB |
+| :ref:`sphx_glr_how_to_optimize_operators_opt_conv_cuda.py` (``opt_conv_cuda.py``) | 00:01.044 | 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 46598cbb1..a36389227 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
=================
-**05:23.619** total execution time for **how_to_tune_with_autoscheduler** files:
+**05:12.383** 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``) | 02:47.429 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_conv2d_layer_cuda.py` (``tune_conv2d_layer_cuda.py``) | 02:35.043 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.686 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_x86.py` (``tune_network_x86.py``) | 01:19.835 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.851 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_cuda.py` (``tune_network_cuda.py``) | 00:42.890 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:16.787 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_sparse_x86.py` (``tune_sparse_x86.py``) | 00:17.751 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.493 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_mali.py` (``tune_network_mali.py``) | 00:08.536 | 0.0 MB |
+----------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.372 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autoscheduler_tune_network_arm.py` (``tune_network_arm.py``) | 00:08.329 | 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 1d69d4a61..fe44d9ed6 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
@@ -205,13 +205,6 @@ file and apply it.
-.. rst-class:: sphx-glr-script-out
-
- .. code-block:: none
-
- .T
-
-
@@ -246,293 +239,684 @@ cooperative fetching, unrolling and operator fusion.
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*784)
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 784)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 784), 81)) && (floormod(((threadIdx.x_1*16) + 55), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 784), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 784), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 785)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 785), 81)) && (floormod(((threadIdx.x_1*16) + 56), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 785), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 785), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 786)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 786), 81)) && (floormod(((threadIdx.x_1*16) + 57), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 786), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 786), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 787)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 787), 81)) && (floormod(((threadIdx.x_1*16) + 58), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 787), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 787), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 788)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 788), 81)) && (floormod(((threadIdx.x_1*16) + 59), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 788), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 788), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 789)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 789), 81)) && (floormod(((threadIdx.x_1*16) + 60), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 789), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 789), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 790)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 790), 81)) && (floormod(((threadIdx.x_1*16) + 61), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 790), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 790), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 791)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 791), 81)) && (floormod(((threadIdx.x_1*16) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 791), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 791), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 792)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)) && (floormod(((threadIdx.x_1*16) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 792), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 793)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 793), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 794), 81)) && (floormod(((threadIdx.x_1*16) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 794), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 795), 81)) && (floormod(((threadIdx.x_1*16) + 66), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 795), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 796), 81)) && (floormod(((threadIdx.x_1*16) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 796), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 797), 81)) && (floormod(((threadIdx.x_1*16) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 797), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 798), 81)) && (floormod(((threadIdx.x_1*16) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 798), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 799), 81)) && (floormod(((threadIdx.x_1*16) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 799), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[(threadIdx.x_2*24)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1177)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1178)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1179)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1180)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1181)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1182)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1183)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1184)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1185)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1186)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1187)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1188)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1189)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1190)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1191)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1192)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1193)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1194)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1195)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1197)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1198)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1199)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- }
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 16) {
- let cse_var_10: int32 = (ff.outer.inner*2)
- let cse_var_9: int32 = (cse_var_10 + 9)
- let cse_var_8: int32 = (cse_var_10 + 8)
- let cse_var_7: int32 = (cse_var_10 + 5)
- let cse_var_6: int32 = (cse_var_10 + 4)
- let cse_var_5: int32 = (cse_var_10 + 13)
- let cse_var_4: int32 = (cse_var_10 + 12)
- let cse_var_3: int32 = (cse_var_10 + 1)
- let cse_var_2: int32 = ((ff.outer.inner*288) + (rc.inner*9))
- {
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1152)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1728)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 144)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 720)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1296)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1872)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1153)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1729)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 145)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 721)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1297)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1873)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1154)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1730)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 146)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 722)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1298)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1874)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 579)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1155)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1731)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 147)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 723)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1299)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1875)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 580)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1156)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1732)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 148)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 724)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1300)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1876)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 581)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1157)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1733)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 149)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 725)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1301)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1877)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 582)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1158)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1734)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 150)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 726)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1302)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1878)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 583)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1159)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1735)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 151)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 727)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1303)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1879)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 584)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1160)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1736)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 152)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 728)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1304)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1880)]))
- }
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod(thre [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 128), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx.x, 7)) + floormod((threadIdx.x_ [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 168), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 336), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 392), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 616), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 672), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 728), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 840), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 896), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 952), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1064), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1120), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1176), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1232), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1288), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1344), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1400), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1456), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1624), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1680), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1736), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1792), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1848), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1904), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1960), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 592), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2072), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 608), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2128), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 624), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2184), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 640), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2240), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 656), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2296), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 672), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2352), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 688), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2408), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 704), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2464), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 736), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2576), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 752), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2632), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6144)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 768), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2688), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 784), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2744), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6400)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 800), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2800), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6528)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 816), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2856), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6656)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 832), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2912), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6784)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 848), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2968), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6912)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7040)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 880), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3080), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 896), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3136), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7296)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 912), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3192), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7424)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 928), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3248), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7552)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 944), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3304), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7680)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 960), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3360), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7808)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 976), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3416), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7936)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 992), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3472), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1024), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3584), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1040), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3640), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1056), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3696), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8576)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1072), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3752), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1088), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3808), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1104), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3864), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1120), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3920), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 9088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1136), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3976), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
}
}
@@ -586,7 +970,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 0.294 ms
+ Execution time of this operator: 0.218 ms
@@ -634,36 +1018,36 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
- conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
- conv2d_nchw_ff_o_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=1)
- conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=128)
+ conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
- conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
- conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+ conv2d_nchw_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=7)
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=1)
- conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
- conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+ conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+ conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+ conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+ conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=4)
- compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
- compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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=128)
+ 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_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+ compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+ compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
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)
@@ -681,14 +1065,14 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=128)
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=16)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
- pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+ pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=128)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -708,272 +1092,608 @@ They can be used for debugging and learning the behavior of the auto-scheduler.
#define int64_t long long
#define uint64_t unsigned long long
#endif
- extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+ extern "C" __global__ void __launch_bounds__(128) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 784)] = (((((9 <= (((((int)threadIdx.x) * 16) + 55) % 81)) && ((((((int)threadIdx.x) * 16) + 55) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 784) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 55) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 785)] = (((((9 <= (((((int)threadIdx.x) * 16) + 56) % 81)) && ((((((int)threadIdx.x) * 16) + 56) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 785) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 56) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 786)] = (((((9 <= (((((int)threadIdx.x) * 16) + 57) % 81)) && ((((((int)threadIdx.x) * 16) + 57) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 786) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 57) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 787)] = (((((9 <= (((((int)threadIdx.x) * 16) + 58) % 81)) && ((((((int)threadIdx.x) * 16) + 58) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 787) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 58) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 788)] = (((((9 <= (((((int)threadIdx.x) * 16) + 59) % 81)) && ((((((int)threadIdx.x) * 16) + 59) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 788) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 59) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 789)] = (((((9 <= (((((int)threadIdx.x) * 16) + 60) % 81)) && ((((((int)threadIdx.x) * 16) + 60) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 789) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 60) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 790)] = (((((9 <= (((((int)threadIdx.x) * 16) + 61) % 81)) && ((((((int)threadIdx.x) * 16) + 61) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 790) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 61) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 791)] = (((((9 <= (((((int)threadIdx.x) * 16) + 62) % 81)) && ((((((int)threadIdx.x) * 16) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 791) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 792)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 16) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 793) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 65) % 81)) && ((((((int)threadIdx.x) * 16) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 66) % 81)) && ((((((int)threadIdx.x) * 16) + 66) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 66) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 67) % 81)) && ((((((int)threadIdx.x) * 16) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 68) % 81)) && ((((((int)threadIdx.x) * 16) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 69) % 81)) && ((((((int)threadIdx.x) * 16) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 70) % 81)) && ((((((int)threadIdx.x) * 16) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1177)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1178)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1179)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1180)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1181)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1182)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1183)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1184)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1185)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1186)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1187)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1188)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1189)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1190)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1191)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1192)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1193)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1194)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1195)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1197)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1198)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1199)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 88) {
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) + 2) % 3)) - 8)] : 0.000000e+00f);
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4736) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4864) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5376) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5888) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6016) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6144)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6272) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 6400)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6528)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6528) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6656)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6784)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6912)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 7040)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7040) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7296)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7424)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7424) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 7552)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7680)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7808)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7936)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 8192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8576)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8576) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 8704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 9088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9088) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
__syncthreads();
- 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 * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((ff_outer_inner * 288) + (rc_inner * 9))]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 576)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1152)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1728)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 720)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1296)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1872)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 577)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1153)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1729)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 721)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1297)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1873)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 578)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1154)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1730)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 722)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1298)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1874)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 579)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1155)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1731)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 723)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1299)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1875)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 580)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1156)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1732)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 724)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1300)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1876)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 581)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1157)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1733)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 725)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1301)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1877)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 582)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1158)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1734)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 726)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1302)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1878)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 583)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1159)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1735)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 727)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1303)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1879)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 584)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1160)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1736)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 728)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1304)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1880)]));
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
}
@@ -1034,7 +1754,7 @@ 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 47.429 seconds)
+ **Total running time of the script:** ( 2 minutes 35.043 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 578243dd2..5a25e1cd0 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)
- 9.8417 9.8570 9.8785 9.7895 0.0379
+ 9.8540 9.8315 9.9087 9.8219 0.0389
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 345391c9f..ae59ddbd5 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)
- 756.0358 755.8824 756.5194 755.7055 0.3495
+ 763.3928 763.1774 764.3128 762.6881 0.6806
@@ -693,7 +693,7 @@ Other Tips
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 1 minutes 19.686 seconds)
+ **Total running time of the script:** ( 1 minutes 19.835 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 e50a2f711..52e7b989d 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
@@ -396,27 +396,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 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) {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 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 (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
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)))
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- 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))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -472,7 +475,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 1.905 ms
+ Execution time of this operator: 1.645 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 6bb28cb4e..f0f9a6975 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
=================
-**00:42.911** total execution time for **how_to_tune_with_autotvm** files:
+**00:43.418** 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``) | 00:42.880 | 0.0 MB |
+| :ref:`sphx_glr_how_to_tune_with_autotvm_tune_conv2d_cuda.py` (``tune_conv2d_cuda.py``) | 00:43.384 | 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_x86.py` (``tune_relay_x86.py``) | 00:00.021 | 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 797b6e4c7..a0b32d9e2 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: 96.52/96.52 result: MeasureResult(costs=(0.0023985371875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8076894283294678, timestamp=1655777059.6730833) [('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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 6 GFLOPS: 42.34/42.34 result: MeasureResult(costs=(0.005467819631578948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.647458791732788, timestamp=1655836731.6531527) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+ No: 7 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 8 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 9 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 10 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 11 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 12 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 13 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 14 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 15 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 16 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 17 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 18 GFLOPS: 0.00/42.34 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: 0.00/96.52 result: Traceback (most recent call last):
+ No: 19 GFLOPS: 0.00/42.34 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: 0x00007f76e5b7efa2
+ 12: 0x00007fca663f5fa2
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: 145.05/145.05 result: MeasureResult(costs=(0.0015960395800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4159400463104248, timestamp=1655777086.052862) [('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: 143.94/143.94 result: MeasureResult(costs=(0.00160826286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4292681217193604, timestamp=1655836758.2018938) [('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: 0.002028
+ Time cost of this operator: 0.001999
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 e9ed05861..251082337 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 315.9 98.72 (1, 2, 10, 10, 3) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.153 0.985 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.943 0.295 (1, 1, 10, 10, 3) 1 1
- Total_time - 319.996 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.2 98.758 (1, 2, 10, 10, 3) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.954 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.93 0.289 (1, 1, 10, 10, 3) 1 1
+ Total_time - 322.202 - - - -
@@ -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 153.5 98.305 (1, 6, 10, 10, 1) 2 1
- tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.724 1.104 (1, 6, 10, 10) 1 1
- tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.591 (1, 1, 10, 10, 3) 1 1
- Total_time - 156.147 - - - -
+ tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 120.4 97.847 (1, 6, 10, 10, 1) 2 1
+ tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.748 1.421 (1, 6, 10, 10) 1 1
+ tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.732 (1, 1, 10, 10, 3) 1 1
+ Total_time - 123.049 - - - -
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 2038433a2..dd3dab1d6 100644
--- a/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
+++ b/docs/_sources/how_to/work_with_microtvm/micro_train.rst.txt
@@ -224,7 +224,7 @@ take about **2 minutes** to download the Stanford Cars, while COCO 2017 validati
.. code-block:: none
- '/tmp/tmp905e758o/images/random'
+ '/tmp/tmp286hadhz/images/random'
@@ -324,8 +324,8 @@ objects to other stuff? We can display some examples from our datasets using ``m
.. code-block:: none
- /tmp/tmp905e758o/images/target contains 8144 images
- /tmp/tmp905e758o/images/random contains 5000 images
+ /tmp/tmp286hadhz/images/target contains 8144 images
+ /tmp/tmp286hadhz/images/random contains 5000 images
@@ -500,13 +500,13 @@ the time on our validation set).
.. code-block:: none
Epoch 1/3
- 328/328 - 55s - loss: 0.2037 - accuracy: 0.9283 - val_loss: 0.1357 - val_accuracy: 0.9585
+ 328/328 - 55s - loss: 0.2344 - accuracy: 0.9208 - val_loss: 0.1605 - val_accuracy: 0.9543
Epoch 2/3
- 328/328 - 52s - loss: 0.0962 - accuracy: 0.9643 - val_loss: 0.1227 - val_accuracy: 0.9664
+ 328/328 - 52s - loss: 0.1006 - accuracy: 0.9623 - val_loss: 0.1323 - val_accuracy: 0.9630
Epoch 3/3
- 328/328 - 52s - loss: 0.0652 - accuracy: 0.9748 - val_loss: 0.1419 - val_accuracy: 0.9569
+ 328/328 - 52s - loss: 0.0629 - accuracy: 0.9764 - val_loss: 0.1169 - val_accuracy: 0.9660
- <keras.callbacks.History object at 0x7fce0c51fb90>
+ <keras.callbacks.History object at 0x7f3940fc4a50>
@@ -863,7 +863,7 @@ Arduino tutorial for how to do that `on GitHub <https://github.com/guberti/tvm-a
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 4 minutes 12.770 seconds)
+ **Total running time of the script:** ( 4 minutes 53.458 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 50f0a6562..4a82f8b83 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
=================
-**04:57.854** total execution time for **how_to_work_with_microtvm** files:
+**05:39.239** total execution time for **how_to_work_with_microtvm** files:
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:12.770 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_train.py` (``micro_train.py``) | 04:53.458 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:41.738 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_autotune.py` (``micro_autotune.py``) | 00:42.314 | 0.0 MB |
+---------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.346 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_microtvm_micro_tflite.py` (``micro_tflite.py``) | 00:03.468 | 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 266948bb5..9f53ced5a 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
=================
-**00:11.139** total execution time for **how_to_work_with_relay** files:
+**00:11.377** 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``) | 00:09.631 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_using_external_lib.py` (``using_external_lib.py``) | 00:09.846 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.503 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_relay_build_gcn.py` (``build_gcn.py``) | 00:01.524 | 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 43277cf1e..f3338d28a 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 0x7fcd8a7414d0>
+ <function my_cuda_math_rule at 0x7f3ac24e6320>
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 4840f5681..b8fb35cbb 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
=================
-**00:03.876** total execution time for **how_to_work_with_schedules** files:
+**00:04.203** total execution time for **how_to_work_with_schedules** files:
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.808 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_intrin_math.py` (``intrin_math.py``) | 00:01.964 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.911 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tensorize.py` (``tensorize.py``) | 00:00.997 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_reduction.py` (``reduction.py``) | 00:00.500 | 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_scan.py` (``scan.py``) | 00:00.485 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_scan.py` (``scan.py``) | 00:00.524 | 0.0 MB |
+------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.099 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_extern_op.py` (``extern_op.py``) | 00:00.100 | 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_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.012 | 0.0 MB |
+| :ref:`sphx_glr_how_to_work_with_schedules_tuple_inputs.py` (``tuple_inputs.py``) | 00:00.013 | 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 4e8c15e5a..a80e183a6 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/tmpcvovfugm/input0.cc'\nsource_filename = \"/tmp/tmpcvovfugm/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/tmp9i0lwnq6/input0.cc'\nsource_filename = \"/tmp/tmp9i0lwnq6/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 91442b311..c68e0e444 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
=================
-**00:20.656** total execution time for **topic_vta_tutorials_autotvm** files:
+**00:21.004** total execution time for **topic_vta_tutorials_autotvm** files:
+---------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.650 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_autotvm_tune_relay_vta.py` (``tune_relay_vta.py``) | 00:20.997 | 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 1387cd32a..002c21dbf 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 22.27s!
+ resnet18_v1 inference graph built in 23.30s!
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 730a55a26..6792966ad 100644
--- a/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
+++ b/docs/_sources/topic/vta/tutorials/frontend/deploy_detection.rst.txt
@@ -335,7 +335,7 @@ The compilation steps are:
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
- yolov3-tiny inference graph built in 15.42s!
+ yolov3-tiny inference graph built in 15.96s!
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 c12e5ffe6..43cdaa486 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
=================
-**01:29.982** total execution time for **topic_vta_tutorials_frontend** files:
+**01:31.727** total execution time for **topic_vta_tutorials_frontend** files:
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:47.321 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_detection.py` (``deploy_detection.py``) | 00:48.025 | 0.0 MB |
+------------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:42.660 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_frontend_deploy_classification.py` (``deploy_classification.py``) | 00:43.702 | 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 84216f0ab..22714c7be 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
=================
-**00:03.131** total execution time for **topic_vta_tutorials_optimize** files:
+**00:03.274** total execution time for **topic_vta_tutorials_optimize** files:
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.768 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_convolution_opt.py` (``convolution_opt.py``) | 00:02.869 | 0.0 MB |
+--------------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.363 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_optimize_matrix_multiply_opt.py` (``matrix_multiply_opt.py``) | 00:00.405 | 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 a01c0782e..83c3f5a92 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
=================
-**00:00.636** total execution time for **topic_vta_tutorials** files:
+**00:00.709** total execution time for **topic_vta_tutorials** files:
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.331 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_matrix_multiply.py` (``matrix_multiply.py``) | 00:00.367 | 0.0 MB |
+---------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.305 | 0.0 MB |
+| :ref:`sphx_glr_topic_vta_tutorials_vta_get_started.py` (``vta_get_started.py``) | 00:00.342 | 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 8ef79808b..4ccea6fd2 100644
--- a/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/auto_scheduler_matmul_x86.rst.txt
@@ -204,6 +204,13 @@ trials, we can load the best schedule from the log file and apply it.
+.. rst-class:: sphx-glr-script-out
+
+ .. code-block:: none
+
+ *E
+
+
@@ -327,7 +334,7 @@ We build the binary and check its correctness and performance.
.. code-block:: none
- Execution time of this operator: 94.076 ms
+ Execution time of this operator: 92.865 ms
diff --git a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
index 8558fbd85..c5965ff0b 100644
--- a/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
+++ b/docs/_sources/tutorial/autotvm_matmul_x86.rst.txt
@@ -449,16 +449,16 @@ reduce variance, we take 5 measurements and average them.
waiting for device...
device available
Get devices for measurement successfully!
- No: 1 GFLOPS: 10.52/10.52 result: MeasureResult(costs=(0.025526263,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5412285327911377, timestamp=1655775952.9237235) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
- No: 2 GFLOPS: 2.86/10.52 result: MeasureResult(costs=(0.0938034704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6478667259216309, timestamp=1655775955.076716) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
- No: 3 GFLOPS: 11.88/11.88 result: MeasureResult(costs=(0.0225954924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5553779602050781, timestamp=1655775956.0894291) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
- No: 4 GFLOPS: 1.87/11.88 result: MeasureResult(costs=(0.14390811220000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4246935844421387, timestamp=1655775959.0420928) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
- No: 5 GFLOPS: 3.69/11.88 result: MeasureResult(costs=(0.07265601299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3002738952636719, timestamp=1655775960.4691656) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
- No: 6 GFLOPS: 1.77/11.88 result: MeasureResult(costs=(0.1514975422,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.596282720565796, timestamp=1655775963.1097283) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
- No: 7 GFLOPS: 0.82/11.88 result: MeasureResult(costs=(0.3285156574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.366232395172119, timestamp=1655775968.522458) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
- No: 8 GFLOPS: 10.69/11.88 result: MeasureResult(costs=(0.0251015612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5441286563873291, timestamp=1655775969.0876489) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
- No: 9 GFLOPS: 1.79/11.88 result: MeasureResult(costs=(0.1499999786,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4982388019561768, timestamp=1655775971.703007) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
- No: 10 GFLOPS: 2.52/11.88 result: MeasureResult(costs=(0.10644707900000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.806854009628296, timestamp=1655775973.5695636) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+ No: 1 GFLOPS: 8.77/8.77 result: MeasureResult(costs=(0.0306049692,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6216588020324707, timestamp=1655835562.5031402) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+ No: 2 GFLOPS: 2.51/8.77 result: MeasureResult(costs=(0.107064644,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8577520847320557, timestamp=1655835564.3776634) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+ No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227650914,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546836853027344, timestamp=1655835565.4025822) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+ No: 4 GFLOPS: 1.46/11.79 result: MeasureResult(costs=(0.1833495256,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.042811870574951, timestamp=1655835568.992751) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+ No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.07353091120000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3120806217193604, timestamp=1655835570.4362006) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+ No: 6 GFLOPS: 1.79/11.79 result: MeasureResult(costs=(0.15037857459999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.565373420715332, timestamp=1655835573.048497) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+ No: 7 GFLOPS: 0.87/11.79 result: MeasureResult(costs=(0.307675731,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.04430627822876, timestamp=1655835578.640404) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+ No: 8 GFLOPS: 10.55/11.79 result: MeasureResult(costs=(0.025443531400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5576968193054199, timestamp=1655835579.2221763) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+ No: 9 GFLOPS: 1.90/11.79 result: MeasureResult(costs=(0.1416071596,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3655643463134766, timestamp=1655835581.709819) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+ No: 10 GFLOPS: 2.74/11.79 result: MeasureResult(costs=(0.0980331616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6731891632080078, timestamp=1655835583.4421256) [('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 144dc5375..70a131ea8 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': 493.62848814001154, 'median': 493.2573527999921, 'std': 0.9040261763734981}
+ {'mean': 493.3181805199956, 'median': 493.2952068499844, 'std': 0.8367690376909532}
@@ -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: 17.52/ 17.52 GFLOPS | Progress: (4/20) | 5.96 s
[Task 1/25] Current/Best: 6.16/ 17.52 GFLOPS | Progress: (8/20) | 8.89 s
[Task 1/25] Current/Best: 11.51/ 22.48 GFLOPS | Progress: (12/20) | 11.31 s
[Task 1/25] Current/Best: 16.85/ 22.77 GFLOPS | Progress: (16/20) | 12.99 s
[Task 1/25] Current/Best: 11.57/ 23.92 GFLOPS | Progress: (20/20) | 14.71 s Done.
-
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.17/ 13.21 GFLOPS | Progress: (4/20) | 3.69 s
[Task 2/25] Current/Best: 14.25/ 18.84 GFLOPS | Progress: (8/20) | 4.97 s
[Task 2/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (12/20) | 6.28 s
[Task 2/25] Current/Best: 12.57/ 21.21 GFLOPS | Progress: (16/20) | 7.56 s
[Task 2/25] Current/Best: 20.08/ 21.21 GFLOPS | Progress: (20/20) | 9.10 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/ 10.56 GFLOPS | Progress: (4/20) | 5.78 s
[Task 3/25] Current/Best: 15.61/ 16.88 GFLOPS | Progress: (8/20) | 7.71 s
[Task 3/25] Current/Best: 14.90/ 16.88 GFLOPS | Progress: (12/20) | 9.44 s
[Task 3/25] Current/Best: 7.20/ 22.06 GFLOPS | Progress: (16/20) | 11.38 s
[Task 3/25] Current/Best: 12.47/ 22.06 GFLOPS | Progress: (20/20) | 15.91 s Done.
-
[Task 4/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 4/25] Current/Best: 9.55/ 20.48 GFLOPS | Progress: (4/20) | 2.32 s
[Task 4/25] Current/Best: 6.86/ 20.48 GFLOPS | Progress: (8/20) | 6.60 s
[Task 4/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (12/20) | 10.99 s
[Task 4/25] Current/Best: 17.42/ 21.97 GFLOPS | Progress: (16/20) | 13.18 s
[Task 4/25] Current/Best: 13.18/ 21.97 GFLOPS | Progress: (20/20) | 15.17 s Done.
-
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.85/ 10.15 GFLOPS | Progress: (4/20) | 2.54 s
[Task 5/25] Current/Best: 11.61/ 11.87 GFLOPS | Progress: (8/20) | 4.59 s
[Task 5/25] Current/Best: 11.56/ 18.09 GFLOPS | Progress: (12/20) | 7.69 s
[Task 5/25] Current/Best: 11.81/ 22.80 GFLOPS | Progress: (16/20) | 9.10 s
[Task 5/25] Current/Best: 11.92/ 22.80 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: 12.28/ 20.78 GFLOPS | Progress: (4/20) | 3.92 s
[Task 6/25] Current/Best: 18.92/ 20.78 GFLOPS | Progress: (8/20) | 5.68 s
[Task 6/25] Current/Best: 13.34/ 20.78 GFLOPS | Progress: (12/20) | 7.60 s
[Task 6/25] Current/Best: 19.98/ 20.78 GFLOPS | Progress: (16/20) | 9.85 s
[Task 6/25] Current/Best: 3.72/ 20.78 GFLOPS | Progress: (20/20) | 12.35 s Done.
-
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 11.16/ 12.96 GFLOPS | Progress: (4/20) | 3.56 s
[Task 7/25] Current/Best: 20.28/ 21.12 GFLOPS | Progress: (8/20) | 5.05 s
[Task 7/25] Current/Best: 15.83/ 21.12 GFLOPS | Progress: (12/20) | 6.98 s
[Task 7/25] Current/Best: 12.26/ 21.12 GFLOPS | Progress: (16/20) | 9.02 s
[Task 7/25] Current/Best: 6.30/ 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: 10.08/ 14.01 GFLOPS | Progress: (4/20) | 2.83 s
[Task 8/25] Current/Best: 9.33/ 14.01 GFLOPS | Progress: (8/20) | 7.61 s
[Task 8/25] Current/Best: 12.60/ 14.01 GFLOPS | Progress: (12/20) | 13.66 s
[Task 8/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (16/20) | 15.74 s
[Task 8/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (20/20) | 22.26 s Done.
-
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.31/ 15.53 GFLOPS | Progress: (4/20) | 11.88 s
[Task 9/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (8/20) | 13.63 s
[Task 9/25] Current/Best: 8.29/ 23.37 GFLOPS | Progress: (12/20) | 15.95 s
[Task 9/25] Current/Best: 17.97/ 23.37 GFLOPS | Progress: (16/20) | 18.60 s
[Task 9/25] Current/Best: 9.06/ 23.37 GFLOPS | Progress: (20/20) | 26.22 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 2.51 s
[Task 10/25] Current/Best: 15.55/ 18.14 GFLOPS | Progress: (8/20) | 4.11 s
[Task 10/25] Current/Best: 12.23/ 18.96 GFLOPS | Progress: (12/20) | 5.63 s
[Task 10/25] Current/Best: 19.11/ 20.34 GFLOPS | Progress: (16/20) | 6.73 s
[Task 10/25] Current/Best: 8.87/ 20.34 GFLOPS | Progress: (20/20
) | 8.26 s Done.
-
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.25/ 18.11 GFLOPS | Progress: (4/20) | 3.22 s
[Task 11/25] Current/Best: 16.87/ 18.11 GFLOPS | Progress: (8/20) | 5.95 s
[Task 11/25] Current/Best: 18.10/ 18.11 GFLOPS | Progress: (12/20) | 7.96 s
[Task 11/25] Current/Best: 13.44/ 21.16 GFLOPS | Progress: (16/20) | 10.65 s
[Task 11/25] Current/Best: 19.39/ 21.48 GFLOPS | Progress: (20/20) | 12.66 s Done.
-
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.81/ 18.07 GFLOPS | Progress: (4/20) | 5.27 s
[Task 12/25] Current/Best: 5.29/ 18.07 GFLOPS | Progress: (8/20) | 8.92 s
[Task 12/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (12/20) | 10.88 s
[Task 12/25] Current/Best: 15.38/ 19.03 GFLOPS | Progress: (16/20) | 13.66 s
[Task 12/25] Current/Best: 15.18/ 19.03 GFLOPS | Progress: (20/20) | 15.58 s Done.
-
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 8.78/ 17.25 GFLOPS | Progress: (4/20) | 3.60 s
[Task 13/25] Current/Best: 16.01/ 20.99 GFLOPS | Progress: (8/20) | 6.00 s
[Task 13/25] Current/Best: 19.20/ 21.54 GFLOPS | Progress: (12/20) | 8.86 s
[Task 13/25] Current/Best: 12.29/ 21.54 GFLOPS | Progress: (16/20) | 12.27 s
[Task 13/25] Current/Best: 18.74/ 21.54 GFLOPS | Progress: (20/20) | 14.51 s Done.
-
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.67/ 13.67 GFLOPS | Progress: (4/20) | 3.18 s
[Task 14/25] Current/Best: 6.11/ 13.67 GFLOPS | Progress: (8/20) | 5.36 s
[Task 14/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (12/20) | 7.91 s
[Task 14/25] Current/Best: 17.06/ 20.57 GFLOPS | Progress: (16/20) | 9.55 s Done.
-
[Task 14/25] Current/Best: 17.32/ 20.57 GFLOPS | Progress: (20/20) | 11.27 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 16.12/ 17.65 GFLOPS | Progress: (4/20) | 2.63 s
[Task 15/25] Current/Best: 13.44/ 18.03 GFLOPS | Progress: (8/20) | 3.97 s
[Task 15/25] Current/Best: 10.39/ 22.25 GFLOPS | Progress: (12/20) | 6.04 s
[Task 15/25] Current/Best: 20.36/ 22.25 GFLOPS | Progress: (16/20) | 8.98 s
[Task 15/25] Current/Best: 9.69/ 22.25 GFLOPS | Progress: (20/20) | 9.95 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (4/20) | 2.99 s
[Task 16/25] Current/Best: 3.04/ 20.46 GFLOPS | Progress: (8/20) | 4.61 s
[Task 16/25] Current/Best: 19.29/ 20.46 GFLOPS | Progress: (12/20) | 5.82 s
[Task 16/25] Current/Best: 18.05/ 20.46 GFLOPS | Progress: (16/20) |
7.18 s
[Task 16/25] Current/Best: 9.96/ 22.21 GFLOPS | Progress: (20/20) | 9.22 s Done.
-
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 13.51/ 18.87 GFLOPS | Progress: (4/20) | 4.68 s
[Task 17/25] Current/Best: 14.36/ 23.23 GFLOPS | Progress: (8/20) | 7.52 s
[Task 17/25] Current/Best: 16.87/ 23.23 GFLOPS | Progress: (12/20) | 9.54 s
[Task 17/25] Current/Best: 16.57/ 23.23 GFLOPS | Progress: (16/20) | 11.69 s
[Task 17/25] Current/Best: 10.04/ 23.23 GFLOPS | Progress: (20/20) | 13.81 s Done.
-
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.40/ 18.10 GFLOPS | Progress: (4/20) | 3.62 s
[Task 18/25] Current/Best: 10.58/ 19.44 GFLOPS | Progress: (8/20) | 7.02 s
[Task 18/25] Current/Best: 18.99/ 19.44 GFLOPS | Progress: (12/20) | 8.95 s
[Task 18/25] Current/Best: 10.06/ 19.44 GFLOPS | Progress: (16/20) | 12.53 s
[Task 18/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (20/20) | 14.02 s Done.
-
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 7.13/ 20.33 GFLOPS | Progress: (4/20) | 5.91 s
[Task 19/25] Current/Best: 2.61/ 20.33 GFLOPS | Progress: (8/20) | 9.17 s
[Task 19/25] Current/Best: 19.75/ 21.73 GFLOPS | Progress: (12/20) | 11.93 s
[Task 19/25] Current/Best: 14.23/ 21.73 GFLOPS | Progress: (16/20) | 14.75 s
[Task 19/25] Current/Best: 2.70/ 23.47 GFLOPS | Progress: (20/20) | 17.59 s Done.
-
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.33/ 15.34 GFLOPS | Progress: (4/20) | 3.25 s Done.
+
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 1/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 6.15 s
[Task 1/25] Current/Best: 6.15/ 17.35 GFLOPS | Progress: (8/20) | 9.13 s
[Task 1/25] Current/Best: 11.50/ 22.73 GFLOPS | Progress: (12/20) | 11.57 s
[Task 1/25] Current/Best: 16.78/ 22.73 GFLOPS | Progress: (16/20) | 13.25 s
[Task 1/25] Current/Best: 11.59/ 23.86 GFLOPS | Progress: (20/20) | 14.99 s Done.
+
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 2/25] Current/Best: 12.02/ 13.05 GFLOPS | Progress: (4/20) | 3.78 s
[Task 2/25] Current/Best: 14.12/ 17.74 GFLOPS | Progress: (8/20) | 5.09 s
[Task 2/25] Current/Best: 20.91/ 20.91 GFLOPS | Progress: (12/20) | 6.41 s
[Task 2/25] Current/Best: 11.87/ 20.91 GFLOPS | Progress: (16/20) | 7.68 s
[Task 2/25] Current/Best: 19.47/ 20.91 GFLOPS | Progress: (20/20) | 9.31 s Done.
+
[Task 3/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.85 s
[Task 3/25] Current/Best: 15.49/ 16.86 GFLOPS | Progress: (8/20) | 7.76 s
[Task 3/25] Current/Best: 14.87/ 16.86 GFLOPS | Progress: (12/20) | 9.51 s
[Task 3/25] Current/Best: 7.17/ 23.72 GFLOPS | Progress: (16/20) | 11.45 s
[Task 3/25] Current/Best: 12.63/ 23.72 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: 9.42/ 19.97 GFLOPS | Progress: (4/20) | 2.35 s
[Task 4/25] Current/Best: 6.88/ 19.97 GFLOPS | Progress: (8/20) | 6.74 s
[Task 4/25] Current/Best: 21.89/ 21.89 GFLOPS | Progress: (12/20) | 11.25 s
[Task 4/25] Current/Best: 17.26/ 21.89 GFLOPS | Progress: (16/20) | 13.51 s
[Task 4/25] Current/Best: 13.14/ 21.89 GFLOPS | Progress: (20/20) | 15.43 s Done.
+
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 5/25] Current/Best: 9.50/ 10.19 GFLOPS | Progress: (4/20) | 2.57 s
[Task 5/25] Current/Best: 11.51/ 12.65 GFLOPS | Progress: (8/20) | 4.65 s
[Task 5/25] Current/Best: 11.11/ 18.14 GFLOPS | Progress: (12/20) | 7.78 s
[Task 5/25] Current/Best: 11.66/ 22.64 GFLOPS | Progress: (16/20) | 9.24 s
[Task 5/25] Current/Best: 11.16/ 22.64 GFLOPS | Progress: (20/20) | 11.14 s Done.
+
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 6/25] Current/Best: 12.24/ 20.85 GFLOPS | Progress: (4/20) | 4.01 s
[Task 6/25] Current/Best: 18.96/ 20.85 GFLOPS | Progress: (8/20) | 5.79 s
[Task 6/25] Current/Best: 13.28/ 20.85 GFLOPS | Progress: (12/20) | 7.73 s
[Task 6/25] Current/Best: 20.01/ 20.85 GFLOPS | Progress: (16/20) | 10.00 s
[Task 6/25] Current/Best: 3.66/ 20.85 GFLOPS | Progress: (20/20) | 12.53 s Done.
+
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 7/25] Current/Best: 10.63/ 12.15 GFLOPS | Progress: (4/20) | 3.53 s
[Task 7/25] Current/Best: 20.22/ 20.88 GFLOPS | Progress: (8/20) | 5.04 s
[Task 7/25] Current/Best: 16.11/ 20.88 GFLOPS | Progress: (12/20) | 6.94 s
[Task 7/25] Current/Best: 12.22/ 20.88 GFLOPS | Progress: (16/20) | 9.00 s
[Task 7/25] Current/Best: 6.26/ 21.69 GFLOPS | Progress: (20/20) | 11.44 s Done.
+
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 8/25] Current/Best: 9.61/ 13.80 GFLOPS | Progress: (4/20) | 2.90 s
[Task 8/25] Current/Best: 9.04/ 13.80 GFLOPS | Progress: (8/20) | 7.69 s
[Task 8/25] Current/Best: 12.54/ 13.80 GFLOPS | Progress: (12/20) | 13.79 s
[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 15.90 s
[Task 8/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (20/20) | 22.57 s Done.
+
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 9/25] Current/Best: 14.29/ 15.76 GFLOPS | Progress: (4/20) | 11.93 s
[Task 9/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (8/20) | 13.74 s
[Task 9/25] Current/Best: 8.20/ 23.21 GFLOPS | Progress: (12/20) | 16.14 s
[Task 9/25] Current/Best: 17.83/ 23.21 GFLOPS | Progress: (16/20) | 18.83 s
[Task 9/25] Current/Best: 8.93/ 23.21 GFLOPS | Progress: (20/20) | 26.66 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.55 s
[Task 10/25] Current/Best: 15.55/ 18.20 GFLOPS | Progress: (8/20) | 4.15 s
[Task 10/25] Current/Best: 12.36/ 18.81 GFLOPS | Progress: (12/20) | 5.69 s
[Task 10/25] Current/Best: 19.03/ 20.30 GFLOPS | Progress: (16/20) | 6.80 s
[Task 10/25] Current/Best: 8.79/ 20.30 GFLOPS | Progress: (20/20
) | 8.33 s Done.
+
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 11/25] Current/Best: 12.26/ 18.03 GFLOPS | Progress: (4/20) | 3.31 s
[Task 11/25] Current/Best: 16.92/ 18.03 GFLOPS | Progress: (8/20) | 6.08 s
[Task 11/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (12/20) | 8.14 s
[Task 11/25] Current/Best: 13.38/ 21.19 GFLOPS | Progress: (16/20) | 10.98 s
[Task 11/25] Current/Best: 19.39/ 21.45 GFLOPS | Progress: (20/20) | 13.04 s Done.
+
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 12/25] Current/Best: 7.74/ 18.08 GFLOPS | Progress: (4/20) | 5.48 s
[Task 12/25] Current/Best: 5.31/ 18.08 GFLOPS | Progress: (8/20) | 9.24 s
[Task 12/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (12/20) | 11.24 s
[Task 12/25] Current/Best: 14.95/ 19.10 GFLOPS | Progress: (16/20) | 14.06 s
[Task 12/25] Current/Best: 15.11/ 19.10 GFLOPS | Progress: (20/20) | 15.98 s Done.
+
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 13/25] Current/Best: 9.04/ 17.28 GFLOPS | Progress: (4/20) | 3.69 s
[Task 13/25] Current/Best: 15.53/ 20.73 GFLOPS | Progress: (8/20) | 6.19 s
[Task 13/25] Current/Best: 18.98/ 21.10 GFLOPS | Progress: (12/20) | 9.13 s
[Task 13/25] Current/Best: 12.17/ 21.10 GFLOPS | Progress: (16/20) | 12.58 s
[Task 13/25] Current/Best: 18.15/ 21.10 GFLOPS | Progress: (20/20) | 14.83 s Done.
+
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.36 s
[Task 14/25] Current/Best: 6.03/ 13.57 GFLOPS | Progress: (8/20) | 5.59 s
[Task 14/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (12/20) | 8.16 s
[Task 14/25] Current/Best: 16.28/ 19.95 GFLOPS | Progress: (16/20) | 9.83 s Done.
+
[Task 14/25] Current/Best: 17.25/ 19.95 GFLOPS | Progress: (20/20) | 11.55 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 15/25] Current/Best: 15.95/ 17.61 GFLOPS | Progress: (4/20) | 2.69 s
[Task 15/25] Current/Best: 14.29/ 17.97 GFLOPS | Progress: (8/20) | 4.05 s
[Task 15/25] Current/Best: 10.35/ 22.28 GFLOPS | Progress: (12/20) | 6.17 s
[Task 15/25] Current/Best: 20.25/ 22.28 GFLOPS | Progress: (16/20) | 9.15 s
[Task 15/25] Current/Best: 9.62/ 22.28 GFLOPS | Progress: (20/20) | 10.14 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 16/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (4/20) | 2.92 s
[Task 16/25] Current/Best: 3.03/ 20.50 GFLOPS | Progress: (8/20) | 4.55 s
[Task 16/25] Current/Best: 19.23/ 20.50 GFLOPS | Progress: (12/20) | 5.78 s
[Task 16/25] Current/Best: 17.56/ 20.50 GFLOPS | Progress: (16/20) |
7.15 s
[Task 16/25] Current/Best: 9.97/ 22.28 GFLOPS | Progress: (20/20) | 9.24 s Done.
+
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 17/25] Current/Best: 12.74/ 18.84 GFLOPS | Progress: (4/20) | 4.72 s
[Task 17/25] Current/Best: 14.40/ 23.03 GFLOPS | Progress: (8/20) | 7.52 s
[Task 17/25] Current/Best: 17.14/ 23.03 GFLOPS | Progress: (12/20) | 9.57 s
[Task 17/25] Current/Best: 16.42/ 23.03 GFLOPS | Progress: (16/20) | 11.74 s
[Task 17/25] Current/Best: 10.01/ 23.03 GFLOPS | Progress: (20/20) | 13.88 s Done.
+
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 18/25] Current/Best: 11.62/ 17.68 GFLOPS | Progress: (4/20) | 3.72 s
[Task 18/25] Current/Best: 10.63/ 19.91 GFLOPS | Progress: (8/20) | 7.25 s
[Task 18/25] Current/Best: 19.07/ 19.91 GFLOPS | Progress: (12/20) | 9.17 s
[Task 18/25] Current/Best: 9.97/ 19.91 GFLOPS | Progress: (16/20) | 12.85 s
[Task 18/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (20/20) | 14.38 s Done.
+
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 19/25] Current/Best: 6.94/ 19.99 GFLOPS | Progress: (4/20) | 6.08 s
[Task 19/25] Current/Best: 2.59/ 19.99 GFLOPS | Progress: (8/20) | 9.36 s
[Task 19/25] Current/Best: 17.31/ 20.73 GFLOPS | Progress: (12/20) | 12.17 s
[Task 19/25] Current/Best: 13.46/ 20.73 GFLOPS | Progress: (16/20) | 15.07 s
[Task 19/25] Current/Best: 2.70/ 23.05 GFLOPS | Progress: (20/20) | 17.84 s Done.
+
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 20/25] Current/Best: 9.01/ 14.95 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-
[Task 20/25] Current/Best: 9.80/ 15.34 GFLOPS | Progress: (8/20) | 6.52 s
[Task 20/25] Current/Best: 2.32/ 16.67 GFLOPS | Progress: (12/20) | 10.56 s
[Task 20/25] Current/Best: 12.21/ 16.67 GFLOPS | Progress: (16/20) | 14.10 s
[Task 20/25] Current/Best: 12.46/ 21.97 GFLOPS | Progress: (20/20) | 16.19 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.56 GFLOPS | Progress: (4/20) | 3.16 s
[Task 21/25] Current/Best: 14.61/ 17.56 GFLOPS | Progress: (8/20) | 4.70 s
[Task 21/25] Current/Best: 1.61/ 17.56 GFLOPS | Progress: (12/20) | 6.81 s
[Task 21/25] Current/Best: 17.92/ 17.92 GFLOPS | Progress: (16/20) | 10.21 s
[Task 21/25] Current/Best: 4.48/ 17.92 GFLOPS | Progress: (20/20) | 17.30 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.03 GFLOPS | Progress: (4/20
) | 2.62 s
[Task 22/25] Current/Best: 8.77/ 21.97 GFLOPS | Progress: (8/20) | 4.59 s
[Task 22/25] Current/Best: 19.96/ 21.97 GFLOPS | Progress: (12/20) | 6.91 s
[Task 22/25] Current/Best: 15.43/ 21.97 GFLOPS | Progress: (16/20) | 8.95 s
[Task 22/25] Current/Best: 14.93/ 21.97 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: 17.54/ 20.71 GFLOPS | Progress: (4/20) | 3.20 s
[Task 23/25] Current/Best: 15.69/ 20.71 GFLOPS | Progress: (8/20) | 6.53 s
[Task 23/25] Current/Best: 20.87/ 21.73 GFLOPS | Progress: (12/20) | 8.33 s
[Task 23/25] Current/Best: 6.39/ 21.73 GFLOPS | Progress: (16/20) | 15.18 s
[Task 23/25] Current/Best: 7.91/ 21.73 GFLOPS | Progress: (20/20) | 19.38 s Done.
-
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.50/ 8.50 GFLOPS | Progress: (4/20) | 11.77 s
[Task 24/25] Current/Best: 2.12/ 8.50 GFLOPS | Progress: (8/20) | 22.74 s
[Task 24/25] Current/Best: 4.46/ 8.50 GFLOPS | Progress: (12/20) | 34.22 s Done.
+
[Task 20/25] Current/Best: 10.19/ 14.95 GFLOPS | Progress: (8/20) | 6.81 s
[Task 20/25] Current/Best: 2.32/ 14.99 GFLOPS | Progress: (12/20) | 10.77 s
[Task 20/25] Current/Best: 12.42/ 14.99 GFLOPS | Progress: (16/20) | 14.44 s
[Task 20/25] Current/Best: 13.35/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 21/25] Current/Best: 6.38/ 17.60 GFLOPS | Progress: (4/20) | 3.22 s
[Task 21/25] Current/Best: 14.47/ 17.60 GFLOPS | Progress: (8/20) | 4.84 s
[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.98 s
[Task 21/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (16/20) | 10.43 s
[Task 21/25] Current/Best: 4.46/ 18.18 GFLOPS | Progress: (20/20) | 17.70 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 22/25] Current/Best: 2.70/ 17.00 GFLOPS | Progress: (4/20
) | 2.69 s
[Task 22/25] Current/Best: 9.23/ 21.93 GFLOPS | Progress: (8/20) | 4.68 s
[Task 22/25] Current/Best: 19.44/ 21.93 GFLOPS | Progress: (12/20) | 7.00 s
[Task 22/25] Current/Best: 15.23/ 21.93 GFLOPS | Progress: (16/20) | 9.08 s
[Task 22/25] Current/Best: 15.17/ 21.93 GFLOPS | Progress: (20/20) | 10.76 s Done.
+
[Task 23/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 23/25] Current/Best: 17.23/ 20.10 GFLOPS | Progress: (4/20) | 3.24 s
[Task 23/25] Current/Best: 15.83/ 20.10 GFLOPS | Progress: (8/20) | 6.52 s
[Task 23/25] Current/Best: 20.70/ 21.23 GFLOPS | Progress: (12/20) | 8.35 s
[Task 23/25] Current/Best: 6.04/ 21.23 GFLOPS | Progress: (16/20) | 15.51 s
[Task 23/25] Current/Best: 7.43/ 21.23 GFLOPS | Progress: (20/20) | 19.80 s Done.
+
[Task 24/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
[Task 24/25] Current/Best: 8.45/ 8.45 GFLOPS | Progress: (4/20) | 11.81 s
[Task 24/25] Current/Best: 2.05/ 8.45 GFLOPS | Progress: (8/20) | 22.84 s
[Task 24/25] Current/Best: 4.47/ 8.45 GFLOPS | Progress: (12/20) | 34.34 s Done.
Done.
-
[Task 24/25] Current/Best: 6.52/ 8.75 GFLOPS | Progress: (16/20) | 39.65 s
[Task 24/25] Current/Best: 3.37/ 8.85 GFLOPS | Progress: (20/20) | 45.56 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) | 11.53 s
[Task 25/25] Current/Best: 5.74/ 7.66 GFLOPS | Progress: (8/20) | 22.77 s
[Task 25/25] Current/Best: 5.99/ 7.66 GFLOPS | Progress: (12/20) | 34.13 s
[Task 25/25] Current/Best: 5.78/ 8.45 GFLOPS | Progress: (16/20) | 35.98 s
[Task 25/25] Current/Best: 2.93/ 8.97 GFLOPS | Progress: (20/20) | 46.65 s
+
[Task 24/25] Current/Best: 7.30/ 8.57 GFLOPS | Progress: (16/20) | 39.93 s
[Task 24/25] Current/Best: 3.34/ 8.72 GFLOPS | Progress: (20/20) | 46.06 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/ 2.76 GFLOPS | Progress: (4/20) | 11.54 s
[Task 25/25] Current/Best: 5.69/ 7.84 GFLOPS | Progress: (8/20) | 22.80 s
[Task 25/25] Current/Best: 5.98/ 7.84 GFLOPS | Progress: (12/20) | 34.26 s
[Task 25/25] Current/Best: 5.85/ 8.53 GFLOPS | Progress: (16/20) | 36.10 s
[Task 25/25] Current/Best: 2.91/ 8.76 GFLOPS | Progress: (20/20) | 46.78 s
@@ -735,8 +735,8 @@ improvement in comparing the optimized model to the unoptimized model.
.. code-block:: none
- optimized: {'mean': 411.8478724999659, 'median': 411.7712770998878, 'std': 0.9912045038640759}
- unoptimized: {'mean': 493.62848814001154, 'median': 493.2573527999921, 'std': 0.9040261763734981}
+ optimized: {'mean': 412.15568752999843, 'median': 412.0211206000022, 'std': 1.3033251613957337}
+ unoptimized: {'mean': 493.3181805199956, 'median': 493.2952068499844, 'std': 0.8367690376909532}
@@ -759,7 +759,7 @@ profiling/benchmarking.
.. rst-class:: sphx-glr-timing
- **Total running time of the script:** ( 10 minutes 9.413 seconds)
+ **Total running time of the script:** ( 10 minutes 16.898 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 32f6da9d1..e72e8c67f 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
- 1.341e-07 secs/op
+ 1.151e-07 secs/op
diff --git a/docs/_sources/tutorial/intro_topi.rst.txt b/docs/_sources/tutorial/intro_topi.rst.txt
index 766869370..9de925cec 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, 0x991bd70)), stage(b, placeholder(b, 0x229e03a0)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
+ [stage(a, placeholder(a, 0x21d5bfb0)), stage(b, placeholder(b, 0x5967e20)), stage(T_add, compute(T_add, body=[(a[ax0, ax1, ax2] + b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min=0, ext=10))], reduce_axis=[], tag=broadcast, attrs={})), stage(T_multiply, compute(T_multiply, body=[(a[ax0, ax1, ax2]*b[ax1, ax2])], axis=[iter_var(ax0, range(min=0, ext=100)), iter_var(ax1, range(min=0, ext=10)), iter_var(ax2, range(min [...]
diff --git a/docs/_sources/tutorial/sg_execution_times.rst.txt b/docs/_sources/tutorial/sg_execution_times.rst.txt
index 9e2c05e81..43fb0b53a 100644
--- a/docs/_sources/tutorial/sg_execution_times.rst.txt
+++ b/docs/_sources/tutorial/sg_execution_times.rst.txt
@@ -5,30 +5,30 @@
Computation times
=================
-**12:50.756** total execution time for **tutorial** files:
+**13:06.551** total execution time for **tutorial** files:
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:09.413 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_relay_x86.py` (``autotvm_relay_x86.py``) | 10:16.898 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 00:58.741 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_expr_get_started.py` (``tensor_expr_get_started.py``) | 01:01.348 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:49.563 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_auto_scheduler_matmul_x86.py` (``auto_scheduler_matmul_x86.py``) | 00:54.278 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:27.806 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_relay_quick_start.py` (``relay_quick_start.py``) | 00:28.055 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:23.940 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_autotvm_matmul_x86.py` (``autotvm_matmul_x86.py``) | 00:24.314 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.659 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.815 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_tensor_ir_blitz_course.py` (``tensor_ir_blitz_course.py``) | 00:00.496 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_intro_topi.py` (``intro_topi.py``) | 00:00.686 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
-| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.137 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_cross_compilation_and_rpc.py` (``cross_compilation_and_rpc.py``) | 00:00.156 | 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_introduction.py` (``introduction.py``) | 00:00.000 | 0.0 MB |
+| :ref:`sphx_glr_tutorial_tvmc_command_line_driver.py` (``tvmc_command_line_driver.py``) | 00:00.000 | 0.0 MB |
+------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_tutorial_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 e862cf15d..43e708b47 100644
--- a/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
+++ b/docs/_sources/tutorial/tensor_expr_get_started.rst.txt
@@ -289,7 +289,7 @@ helper function to run a profile of the TVM generated code.
.. code-block:: none
Numpy running time: 0.000008
- naive: 0.000007
+ 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: 0.000006
+ parallel: 0.000007
@@ -499,10 +499,10 @@ We can now compare the different schedules
.. code-block:: none
Operator Timing Performance
- numpy 8.096700003079605e-06 1.0
- naive 6.7355999999999995e-06 0.8318944752106529
- parallel 6.0934e-06 0.7525782105897905
- vector 2.46222e-05 3.0410167093550298
+ numpy 8.49314000333834e-06 1.0
+ naive 5.8682e-06 0.6909340947745389
+ parallel 6.9630999999999995e-06 0.81984990206956
+ vector 2.46067e-05 2.897244127652201
@@ -923,7 +923,7 @@ matrix multiplication.
.. code-block:: none
- Numpy running time: 0.018073
+ Numpy running time: 0.018600
@@ -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: 3.252220
+ none: 3.444738
@@ -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: 0.304340
+ blocking: 0.301225
@@ -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: 0.340588
+ vectorization: 0.341921
@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: 0.115821
+ loop permutation: 0.116185
@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: 0.109037
+ array packing: 0.109744
@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: 0.110482
+ block caching: 0.111014
@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: 0.144425
+ parallelization: 0.144801
@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 3.2522204115999997 1.0
- blocking 0.3043404771 0.09357929001813046
- vectorization 0.34058763680000004 0.10472464768537647
- loop permutation 0.11582084649999999 0.03561285271037932
- array packing 0.1090369774 0.03352693347938153
- block caching 0.11048191589999998 0.033971226398411915
- parallelization 0.14442546350000002 0.04440826426919411
+ none 3.4447377495 1.0
+ blocking 0.30122492430000003 0.08744495117044034
+ vectorization 0.3419212723 0.09925901394079406
+ loop permutation 0.1161852248 0.03372832222623164
+ array packing 0.1097442622 0.031858524561392015
+ block caching 0.11101397660000001 0.03222711993565071
+ parallelization 0.1448007164 0.04203533822597023
@@ -1673,6 +1673,11 @@ operations with tunable parameters that allows you to automatically optimize
the computation for specific platforms.
+.. rst-class:: sphx-glr-timing
+
+ **Total running time of the script:** ( 1 minutes 1.348 seconds)
+
+
.. _sphx_glr_download_tutorial_tensor_expr_get_started.py:
.. only:: html
diff --git a/docs/commit_hash b/docs/commit_hash
index 47eaa3add..7fe6bc39a 100644
--- a/docs/commit_hash
+++ b/docs/commit_hash
@@ -1 +1 @@
-9ff2a5e796b9cac0bdf05bfd600c50ade9728f1f
+9e58af2abe2cbd1305c6067e02c95f68756e8165
diff --git a/docs/how_to/compile_models/from_mxnet.html b/docs/how_to/compile_models/from_mxnet.html
index 16cc0c5f0..cbc1e389c 100644
--- a/docs/how_to/compile_models/from_mxnet.html
+++ b/docs/how_to/compile_models/from_mxnet.html
@@ -403,7 +403,7 @@ to download the full example code</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"x"</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#tuple" title="builtins.tuple" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">x</span><span class="o">.</span><span class="n">shape</span></a><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_from_mxnet_001.png" srcset="../../_images/sphx_glr_from_mxnet_001.png" alt="from mxnet" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/resnet18_v1-a0666292.zip7c678cb0-de9e-43d6-a903-ae5d0831a9f1 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.zip8471296b-714d-4d7b-8c25-e1543c5e83fe 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 d333b2cac..b1a1f26c3 100644
--- a/docs/how_to/compile_models/from_oneflow.html
+++ b/docs/how_to/compile_models/from_oneflow.html
@@ -408,65 +408,92 @@ python3 -m pip install -f https://release.oneflow.info <span class="nv">oneflow<
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/ResNet/resnet18.zip" to /workspace/.oneflow/flowvision_cache/resnet18.zip
0%| | 0.00/41.5M [00:00<?, ?B/s]
- 0%| | 16.0k/41.5M [00:00<07:46, 93.2kB/s]
- 0%| | 48.0k/41.5M [00:00<04:54, 147kB/s]
- 0%| | 104k/41.5M [00:00<03:10, 228kB/s]
- 1%| | 216k/41.5M [00:00<01:49, 394kB/s]
- 1%|1 | 432k/41.5M [00:00<01:01, 703kB/s]
- 2%|1 | 712k/41.5M [00:01<00:42, 1.02MB/s]
- 2%|2 | 0.98M/41.5M [00:01<00:34, 1.23MB/s]
- 3%|3 | 1.27M/41.5M [00:01<00:30, 1.38MB/s]
- 4%|3 | 1.58M/41.5M [00:01<00:27, 1.53MB/s]
- 5%|4 | 1.90M/41.5M [00:01<00:25, 1.64MB/s]
- 5%|5 | 2.24M/41.5M [00:01<00:23, 1.76MB/s]
- 6%|6 | 2.60M/41.5M [00:02<00:21, 1.87MB/s]
- 7%|7 | 2.98M/41.5M [00:02<00:20, 1.98MB/s]
- 8%|8 | 3.38M/41.5M [00:02<00:19, 2.09MB/s]
- 9%|9 | 3.78M/41.5M [00:02<00:18, 2.19MB/s]
- 10%|# | 4.22M/41.5M [00:02<00:16, 2.31MB/s]
- 11%|#1 | 4.67M/41.5M [00:03<00:15, 2.42MB/s]
- 12%|#2 | 5.15M/41.5M [00:03<00:14, 2.54MB/s]
- 14%|#3 | 5.66M/41.5M [00:03<00:13, 2.68MB/s]
- 15%|#4 | 6.19M/41.5M [00:03<00:13, 2.82MB/s]
- 16%|#6 | 6.73M/41.5M [00:03<00:12, 2.95MB/s]
- 18%|#7 | 7.32M/41.5M [00:03<00:11, 3.10MB/s]
- 19%|#9 | 7.93M/41.5M [00:04<00:10, 3.26MB/s]
- 21%|## | 8.57M/41.5M [00:04<00:10, 3.42MB/s]
- 22%|##2 | 9.24M/41.5M [00:04<00:08, 4.11MB/s]
- 23%|##3 | 9.67M/41.5M [00:04<00:08, 4.07MB/s]
- 24%|##4 | 10.1M/41.5M [00:04<00:08, 3.79MB/s]
- 26%|##5 | 10.7M/41.5M [00:04<00:07, 4.37MB/s]
- 27%|##6 | 11.2M/41.5M [00:04<00:07, 4.36MB/s]
- 28%|##7 | 11.6M/41.5M [00:04<00:07, 4.01MB/s]
- 30%|##9 | 12.3M/41.5M [00:05<00:06, 4.78MB/s]
- 31%|### | 12.8M/41.5M [00:05<00:06, 4.81MB/s]
- 32%|###2 | 13.3M/41.5M [00:05<00:06, 4.42MB/s]
- 34%|###3 | 14.0M/41.5M [00:05<00:05, 5.27MB/s]
- 35%|###5 | 14.6M/41.5M [00:05<00:05, 5.29MB/s]
- 36%|###6 | 15.1M/41.5M [00:05<00:05, 4.81MB/s]
- 39%|###8 | 16.0M/41.5M [00:05<00:04, 5.79MB/s]
- 40%|###9 | 16.6M/41.5M [00:05<00:04, 5.84MB/s]
- 41%|####1 | 17.2M/41.5M [00:06<00:04, 5.31MB/s]
- 44%|####3 | 18.1M/41.5M [00:06<00:03, 6.42MB/s]
- 45%|####5 | 18.8M/41.5M [00:06<00:03, 6.47MB/s]
- 47%|####6 | 19.4M/41.5M [00:06<00:03, 5.87MB/s]
- 49%|####9 | 20.5M/41.5M [00:06<00:03, 5.99MB/s]
- 52%|#####2 | 21.7M/41.5M [00:06<00:03, 6.52MB/s]
- 56%|#####5 | 23.1M/41.5M [00:06<00:02, 6.97MB/s]
- 59%|#####8 | 24.5M/41.5M [00:07<00:02, 7.40MB/s]
- 62%|######2 | 25.9M/41.5M [00:07<00:02, 7.82MB/s]
- 66%|######6 | 27.4M/41.5M [00:07<00:01, 8.11MB/s]
- 70%|######9 | 28.9M/41.5M [00:07<00:01, 8.28MB/s]
- 73%|#######3 | 30.3M/41.5M [00:07<00:01, 8.42MB/s]
- 77%|#######6 | 31.8M/41.5M [00:07<00:01, 8.51MB/s]
- 80%|######## | 33.3M/41.5M [00:08<00:01, 8.58MB/s]
- 84%|########3 | 34.8M/41.5M [00:08<00:00, 8.62MB/s]
- 87%|########7 | 36.2M/41.5M [00:08<00:00, 8.66MB/s]
- 91%|######### | 37.7M/41.5M [00:08<00:00, 9.88MB/s]
- 93%|#########3| 38.7M/41.5M [00:08<00:00, 9.81MB/s]
- 96%|#########5| 39.7M/41.5M [00:08<00:00, 8.99MB/s]
- 98%|#########7| 40.7M/41.5M [00:09<00:00, 7.94MB/s]
-100%|##########| 41.5M/41.5M [00:09<00:00, 4.81MB/s]
+ 0%| | 16.0k/41.5M [00:00<07:48, 92.8kB/s]
+ 0%| | 48.0k/41.5M [00:00<04:55, 147kB/s]
+ 0%| | 80.0k/41.5M [00:00<04:24, 164kB/s]
+ 0%| | 136k/41.5M [00:00<03:10, 227kB/s]
+ 1%| | 232k/41.5M [00:00<02:05, 346kB/s]
+ 1%| | 336k/41.5M [00:01<01:39, 432kB/s]
+ 1%|1 | 440k/41.5M [00:01<01:28, 487kB/s]
+ 1%|1 | 544k/41.5M [00:01<01:22, 524kB/s]
+ 2%|1 | 664k/41.5M [00:01<01:14, 577kB/s]
+ 2%|1 | 784k/41.5M [00:01<01:09, 613kB/s]
+ 2%|2 | 904k/41.5M [00:01<01:06, 638kB/s]
+ 2%|2 | 1.02M/41.5M [00:02<01:02, 683kB/s]
+ 3%|2 | 1.15M/41.5M [00:02<00:59, 714kB/s]
+ 3%|3 | 1.30M/41.5M [00:02<00:55, 764kB/s]
+ 3%|3 | 1.45M/41.5M [00:02<00:52, 798kB/s]
+ 4%|3 | 1.60M/41.5M [00:02<00:49, 837kB/s]
+ 4%|4 | 1.77M/41.5M [00:03<00:47, 877kB/s]
+ 5%|4 | 1.95M/41.5M [00:03<00:44, 933kB/s]
+ 5%|5 | 2.12M/41.5M [00:03<00:42, 972kB/s]
+ 6%|5 | 2.31M/41.5M [00:03<00:40, 1.01MB/s]
+ 6%|6 | 2.52M/41.5M [00:03<00:38, 1.07MB/s]
+ 7%|6 | 2.72M/41.5M [00:03<00:36, 1.11MB/s]
+ 7%|7 | 2.93M/41.5M [00:04<00:35, 1.15MB/s]
+ 8%|7 | 3.15M/41.5M [00:04<00:33, 1.19MB/s]
+ 8%|8 | 3.38M/41.5M [00:04<00:31, 1.25MB/s]
+ 9%|8 | 3.62M/41.5M [00:04<00:30, 1.31MB/s]
+ 9%|9 | 3.88M/41.5M [00:04<00:28, 1.37MB/s]
+ 10%|9 | 4.15M/41.5M [00:04<00:27, 1.43MB/s]
+ 11%|# | 4.43M/41.5M [00:05<00:25, 1.50MB/s]
+ 11%|#1 | 4.73M/41.5M [00:05<00:24, 1.58MB/s]
+ 12%|#2 | 5.03M/41.5M [00:05<00:23, 1.65MB/s]
+ 13%|#2 | 5.35M/41.5M [00:05<00:20, 1.85MB/s]
+ 14%|#3 | 5.69M/41.5M [00:05<00:18, 2.08MB/s]
+ 15%|#4 | 6.04M/41.5M [00:05<00:16, 2.25MB/s]
+ 15%|#5 | 6.27M/41.5M [00:06<00:17, 2.11MB/s]
+ 16%|#5 | 6.48M/41.5M [00:06<00:20, 1.82MB/s]
+ 16%|#6 | 6.80M/41.5M [00:06<00:19, 1.85MB/s]
+ 17%|#7 | 7.19M/41.5M [00:06<00:17, 2.00MB/s]
+ 18%|#8 | 7.59M/41.5M [00:06<00:16, 2.13MB/s]
+ 19%|#9 | 8.01M/41.5M [00:06<00:15, 2.23MB/s]
+ 20%|## | 8.45M/41.5M [00:07<00:14, 2.34MB/s]
+ 21%|##1 | 8.90M/41.5M [00:07<00:12, 2.66MB/s]
+ 23%|##2 | 9.35M/41.5M [00:07<00:11, 2.90MB/s]
+ 24%|##3 | 9.81M/41.5M [00:07<00:10, 3.13MB/s]
+ 24%|##4 | 10.1M/41.5M [00:07<00:11, 2.87MB/s]
+ 25%|##5 | 10.4M/41.5M [00:07<00:13, 2.47MB/s]
+ 26%|##6 | 10.9M/41.5M [00:07<00:11, 2.80MB/s]
+ 27%|##7 | 11.4M/41.5M [00:08<00:09, 3.21MB/s]
+ 28%|##8 | 11.7M/41.5M [00:08<00:09, 3.32MB/s]
+ 29%|##9 | 12.1M/41.5M [00:08<00:10, 2.83MB/s]
+ 30%|### | 12.6M/41.5M [00:08<00:09, 3.17MB/s]
+ 32%|###1 | 13.2M/41.5M [00:08<00:08, 3.65MB/s]
+ 33%|###2 | 13.6M/41.5M [00:08<00:07, 3.76MB/s]
+ 34%|###3 | 13.9M/41.5M [00:08<00:09, 3.20MB/s]
+ 35%|###4 | 14.5M/41.5M [00:08<00:07, 3.57MB/s]
+ 36%|###6 | 15.1M/41.5M [00:09<00:06, 4.29MB/s]
+ 38%|###7 | 15.6M/41.5M [00:09<00:06, 4.11MB/s]
+ 39%|###8 | 16.0M/41.5M [00:09<00:07, 3.52MB/s]
+ 40%|#### | 16.6M/41.5M [00:09<00:06, 4.03MB/s]
+ 42%|####1 | 17.4M/41.5M [00:09<00:05, 4.89MB/s]
+ 43%|####3 | 17.9M/41.5M [00:09<00:05, 4.68MB/s]
+ 44%|####4 | 18.4M/41.5M [00:09<00:06, 4.01MB/s]
+ 46%|####6 | 19.1M/41.5M [00:10<00:05, 4.62MB/s]
+ 48%|####8 | 20.0M/41.5M [00:10<00:04, 5.64MB/s]
+ 50%|####9 | 20.6M/41.5M [00:10<00:04, 5.38MB/s]
+ 51%|##### | 21.1M/41.5M [00:10<00:04, 4.60MB/s]
+ 53%|#####2 | 22.0M/41.5M [00:10<00:03, 5.31MB/s]
+ 55%|#####5 | 23.0M/41.5M [00:10<00:02, 6.50MB/s]
+ 57%|#####6 | 23.6M/41.5M [00:10<00:03, 6.18MB/s]
+ 58%|#####8 | 24.3M/41.5M [00:10<00:03, 5.31MB/s]
+ 61%|###### | 25.2M/41.5M [00:11<00:02, 6.09MB/s]
+ 64%|######3 | 26.4M/41.5M [00:11<00:02, 7.40MB/s]
+ 65%|######5 | 27.1M/41.5M [00:11<00:02, 7.03MB/s]
+ 67%|######7 | 27.9M/41.5M [00:11<00:02, 6.05MB/s]
+ 70%|######9 | 28.9M/41.5M [00:11<00:01, 6.86MB/s]
+ 73%|#######2 | 30.1M/41.5M [00:11<00:01, 8.26MB/s]
+ 75%|#######4 | 31.0M/41.5M [00:11<00:01, 7.72MB/s]
+ 77%|#######6 | 31.8M/41.5M [00:12<00:01, 6.66MB/s]
+ 79%|#######9 | 33.0M/41.5M [00:12<00:01, 6.90MB/s]
+ 83%|########2 | 34.4M/41.5M [00:12<00:00, 7.49MB/s]
+ 87%|########6 | 35.9M/41.5M [00:12<00:00, 7.88MB/s]
+ 90%|######### | 37.4M/41.5M [00:12<00:00, 9.39MB/s]
+ 93%|#########3| 38.7M/41.5M [00:12<00:00, 10.3MB/s]
+ 96%|#########5| 39.8M/41.5M [00:12<00:00, 9.13MB/s]
+ 98%|#########8| 40.7M/41.5M [00:13<00:00, 7.96MB/s]
+100%|##########| 41.5M/41.5M [00:13<00:00, 3.32MB/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 1bbfb259d..c3bbdd983 100644
--- a/docs/how_to/compile_models/from_paddle.html
+++ b/docs/how_to/compile_models/from_paddle.html
@@ -469,7 +469,7 @@ A quick solution is</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>TVM prediction top-1 id: 282, class name: 282: 'tiger cat',
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.300 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 16.093 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 0c5cbe06c..8492e2d43 100644
--- a/docs/how_to/compile_models/from_pytorch.html
+++ b/docs/how_to/compile_models/from_pytorch.html
@@ -390,8 +390,9 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /workspace/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth
0%| | 0.00/44.7M [00:00<?, ?B/s]
- 45%|####5 | 20.2M/44.7M [00:00<00:00, 211MB/s]
-100%|##########| 44.7M/44.7M [00:00<00:00, 244MB/s]
+ 29%|##8 | 12.7M/44.7M [00:00<00:00, 134MB/s]
+ 71%|#######1 | 31.8M/44.7M [00:00<00:00, 172MB/s]
+100%|##########| 44.7M/44.7M [00:00<00:00, 175MB/s]
</pre></div>
</div>
</div>
diff --git a/docs/how_to/compile_models/from_tensorflow.html b/docs/how_to/compile_models/from_tensorflow.html
index 874c7e960..8d1355860 100644
--- a/docs/how_to/compile_models/from_tensorflow.html
+++ b/docs/how_to/compile_models/from_tensorflow.html
@@ -612,6 +612,7 @@ banana (score = 0.00022)
desk (score = 0.00019)
</pre></div>
</div>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 2.200 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 2c8b06d3d..2095f62d4 100644
--- a/docs/how_to/compile_models/sg_execution_times.html
+++ b/docs/how_to/compile_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-compile-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:17.291</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
+<p><strong>06:02.276</strong> total execution time for <strong>how_to_compile_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,43 +312,43 @@
</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>01:06.300</p></td>
+<td><p>01:16.093</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>00:59.282</p></td>
+<td><p>01:02.200</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>00:55.408</p></td>
+<td><p>00:58.148</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>00:34.374</p></td>
+<td><p>00:38.774</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>00:23.654</p></td>
+<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>00:37.609</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>00:22.174</p></td>
+<tr class="row-even"><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>00:23.928</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>00:21.239</p></td>
+<tr class="row-odd"><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>00:22.722</p></td>
<td><p>0.0 MB</p></td>
</tr>
-<tr class="row-even"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
-<td><p>00:18.242</p></td>
+<tr class="row-even"><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>00:21.724</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>00:14.406</p></td>
+<tr class="row-odd"><td><p><a class="reference internal" href="from_pytorch.html#sphx-glr-how-to-compile-models-from-pytorch-py"><span class="std std-ref">Compile PyTorch Models</span></a> (<code class="docutils literal notranslate"><span class="pre">from_pytorch.py</span></code>)</p></td>
+<td><p>00:18.671</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>00:02.214</p></td>
+<td><p>00:02.407</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 38314e225..9de494bb2 100644
--- a/docs/how_to/deploy_models/deploy_model_on_android.html
+++ b/docs/how_to/deploy_models/deploy_model_on_android.html
@@ -629,7 +629,7 @@ to the remote android device.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 15.8870 15.8812 16.0615 15.7296 0.0960
+ 15.9824 16.0376 16.1860 15.7171 0.1692
</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 d5a3b3990..b52309977 100644
--- a/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
+++ b/docs/how_to/deploy_models/deploy_object_detection_pytorch.html
@@ -412,56 +412,71 @@ be unstable.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading: "https://download.pytorch.org/models/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth" to /workspace/.cache/torch/hub/checkpoints/maskrcnn_resnet50_fpn_coco-bf2d0c1e.pth
0%| | 0.00/170M [00:00<?, ?B/s]
- 1%| | 1.12M/170M [00:00<00:15, 11.5MB/s]
- 2%|2 | 3.44M/170M [00:00<00:09, 18.7MB/s]
- 4%|3 | 6.12M/170M [00:00<00:07, 22.9MB/s]
- 5%|4 | 8.32M/170M [00:00<00:07, 22.7MB/s]
- 6%|6 | 10.5M/170M [00:00<00:07, 21.7MB/s]
- 9%|8 | 14.4M/170M [00:00<00:05, 28.1MB/s]
- 10%|# | 17.3M/170M [00:00<00:05, 27.0MB/s]
- 12%|#1 | 19.9M/170M [00:00<00:06, 25.9MB/s]
- 14%|#3 | 23.7M/170M [00:00<00:05, 29.8MB/s]
- 16%|#6 | 27.4M/170M [00:01<00:04, 32.5MB/s]
- 18%|#8 | 30.6M/170M [00:01<00:05, 28.1MB/s]
- 20%|#9 | 33.4M/170M [00:01<00:05, 27.1MB/s]
- 21%|##1 | 36.1M/170M [00:01<00:05, 25.1MB/s]
- 23%|##2 | 38.5M/170M [00:01<00:05, 23.2MB/s]
- 24%|##4 | 41.2M/170M [00:01<00:05, 24.3MB/s]
- 26%|##5 | 43.6M/170M [00:01<00:06, 20.8MB/s]
- 28%|##7 | 47.1M/170M [00:01<00:05, 24.6MB/s]
- 31%|###1 | 52.9M/170M [00:02<00:03, 34.0MB/s]
- 33%|###3 | 56.5M/170M [00:02<00:03, 35.0MB/s]
- 35%|###5 | 60.0M/170M [00:02<00:03, 29.3MB/s]
- 37%|###7 | 63.1M/170M [00:02<00:04, 27.2MB/s]
- 39%|###9 | 66.9M/170M [00:02<00:03, 30.3MB/s]
- 42%|####2 | 71.6M/170M [00:02<00:02, 34.7MB/s]
- 44%|####4 | 75.5M/170M [00:02<00:02, 36.3MB/s]
- 47%|####6 | 79.1M/170M [00:02<00:02, 32.0MB/s]
- 50%|####9 | 84.3M/170M [00:03<00:02, 37.6MB/s]
- 52%|#####1 | 88.1M/170M [00:03<00:02, 30.8MB/s]
- 54%|#####3 | 91.4M/170M [00:03<00:03, 26.9MB/s]
- 55%|#####5 | 94.2M/170M [00:03<00:03, 25.9MB/s]
- 58%|#####7 | 98.5M/170M [00:03<00:02, 30.0MB/s]
- 60%|#####9 | 102M/170M [00:03<00:02, 28.2MB/s]
- 62%|######1 | 105M/170M [00:03<00:02, 29.5MB/s]
- 63%|######3 | 108M/170M [00:04<00:02, 27.0MB/s]
- 65%|######5 | 110M/170M [00:04<00:02, 25.3MB/s]
- 67%|######6 | 113M/170M [00:04<00:02, 25.1MB/s]
- 68%|######8 | 116M/170M [00:04<00:02, 26.2MB/s]
- 70%|######9 | 119M/170M [00:04<00:02, 26.2MB/s]
- 71%|#######1 | 121M/170M [00:04<00:02, 24.8MB/s]
- 74%|#######4 | 126M/170M [00:04<00:01, 32.5MB/s]
- 77%|#######6 | 130M/170M [00:04<00:01, 34.2MB/s]
- 80%|#######9 | 135M/170M [00:04<00:00, 39.6MB/s]
- 82%|########1 | 139M/170M [00:05<00:00, 39.3MB/s]
- 85%|########4 | 144M/170M [00:05<00:00, 41.9MB/s]
- 87%|########6 | 148M/170M [00:05<00:00, 32.4MB/s]
- 89%|########8 | 151M/170M [00:05<00:00, 31.2MB/s]
- 92%|#########1| 156M/170M [00:05<00:00, 36.3MB/s]
- 94%|#########4| 160M/170M [00:05<00:00, 37.7MB/s]
- 97%|#########7| 165M/170M [00:05<00:00, 41.1MB/s]
- 99%|#########9| 169M/170M [00:05<00:00, 41.4MB/s]
-100%|##########| 170M/170M [00:05<00:00, 30.4MB/s]
+ 2%|1 | 2.94M/170M [00:00<00:06, 25.2MB/s]
+ 3%|3 | 5.65M/170M [00:00<00:07, 23.5MB/s]
+ 5%|4 | 8.15M/170M [00:00<00:06, 24.3MB/s]
+ 6%|6 | 10.6M/170M [00:00<00:06, 24.6MB/s]
+ 8%|7 | 13.6M/170M [00:00<00:06, 24.4MB/s]
+ 9%|9 | 15.9M/170M [00:00<00:07, 22.5MB/s]
+ 11%|#1 | 19.0M/170M [00:00<00:06, 25.2MB/s]
+ 13%|#2 | 21.6M/170M [00:00<00:06, 25.5MB/s]
+ 14%|#4 | 24.4M/170M [00:01<00:05, 26.6MB/s]
+ 17%|#6 | 28.4M/170M [00:01<00:05, 28.0MB/s]
+ 18%|#8 | 31.1M/170M [00:01<00:05, 27.0MB/s]
+ 20%|#9 | 33.7M/170M [00:01<00:05, 26.2MB/s]
+ 21%|##1 | 36.5M/170M [00:01<00:05, 27.0MB/s]
+ 23%|##3 | 39.1M/170M [00:01<00:05, 25.6MB/s]
+ 25%|##5 | 42.5M/170M [00:01<00:04, 28.2MB/s]
+ 27%|##6 | 45.3M/170M [00:01<00:04, 28.3MB/s]
+ 28%|##8 | 48.0M/170M [00:01<00:05, 23.6MB/s]
+ 30%|##9 | 50.7M/170M [00:02<00:05, 24.7MB/s]
+ 32%|###2 | 54.8M/170M [00:02<00:04, 29.0MB/s]
+ 34%|###3 | 57.6M/170M [00:02<00:04, 28.8MB/s]
+ 36%|###5 | 60.9M/170M [00:02<00:03, 30.1MB/s]
+ 38%|###8 | 64.9M/170M [00:02<00:03, 33.4MB/s]
+ 40%|#### | 68.2M/170M [00:02<00:04, 22.6MB/s]
+ 42%|####2 | 71.5M/170M [00:02<00:04, 25.3MB/s]
+ 44%|####3 | 74.4M/170M [00:02<00:04, 24.8MB/s]
+ 45%|####5 | 77.2M/170M [00:03<00:03, 25.9MB/s]
+ 48%|####7 | 81.1M/170M [00:03<00:03, 29.7MB/s]
+ 50%|####9 | 84.5M/170M [00:03<00:02, 31.3MB/s]
+ 52%|#####1 | 87.7M/170M [00:03<00:03, 27.7MB/s]
+ 53%|#####3 | 90.5M/170M [00:03<00:03, 23.8MB/s]
+ 55%|#####4 | 93.0M/170M [00:03<00:03, 21.8MB/s]
+ 56%|#####6 | 95.2M/170M [00:03<00:03, 21.1MB/s]
+ 57%|#####7 | 97.3M/170M [00:04<00:03, 20.4MB/s]
+ 58%|#####8 | 99.3M/170M [00:04<00:03, 20.0MB/s]
+ 60%|#####9 | 102M/170M [00:04<00:03, 20.8MB/s]
+ 61%|###### | 104M/170M [00:04<00:03, 20.3MB/s]
+ 62%|######2 | 106M/170M [00:04<00:03, 20.3MB/s]
+ 63%|######3 | 108M/170M [00:04<00:03, 18.2MB/s]
+ 65%|######4 | 110M/170M [00:04<00:03, 19.9MB/s]
+ 66%|######6 | 113M/170M [00:04<00:02, 22.0MB/s]
+ 68%|######7 | 115M/170M [00:04<00:02, 22.9MB/s]
+ 69%|######9 | 118M/170M [00:04<00:02, 23.8MB/s]
+ 71%|####### | 120M/170M [00:05<00:03, 17.3MB/s]
+ 72%|#######1 | 122M/170M [00:05<00:03, 15.4MB/s]
+ 73%|#######2 | 124M/170M [00:05<00:03, 16.0MB/s]
+ 74%|#######3 | 125M/170M [00:05<00:03, 15.5MB/s]
+ 75%|#######4 | 127M/170M [00:05<00:02, 16.3MB/s]
+ 76%|#######6 | 130M/170M [00:05<00:02, 19.1MB/s]
+ 78%|#######7 | 132M/170M [00:05<00:01, 20.1MB/s]
+ 79%|#######9 | 134M/170M [00:06<00:01, 20.6MB/s]
+ 81%|######## | 137M/170M [00:06<00:01, 23.1MB/s]
+ 83%|########3 | 141M/170M [00:06<00:01, 27.7MB/s]
+ 85%|########5 | 144M/170M [00:06<00:00, 29.1MB/s]
+ 87%|########6 | 147M/170M [00:06<00:00, 26.2MB/s]
+ 88%|########8 | 150M/170M [00:06<00:00, 21.7MB/s]
+ 90%|########9 | 152M/170M [00:06<00:00, 21.8MB/s]
+ 91%|######### | 154M/170M [00:06<00:00, 21.2MB/s]
+ 92%|#########2| 157M/170M [00:07<00:00, 22.8MB/s]
+ 94%|#########3| 159M/170M [00:07<00:00, 21.7MB/s]
+ 95%|#########4| 161M/170M [00:07<00:00, 17.9MB/s]
+ 96%|#########6| 163M/170M [00:07<00:00, 16.6MB/s]
+ 97%|#########7| 165M/170M [00:07<00:00, 17.8MB/s]
+ 98%|#########8| 167M/170M [00:07<00:00, 17.4MB/s]
+100%|#########9| 169M/170M [00:07<00:00, 19.0MB/s]
+100%|##########| 170M/170M [00:07<00:00, 22.8MB/s]
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py:3878: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
for i in range(dim)
/usr/local/lib/python3.7/dist-packages/torchvision/models/detection/anchor_utils.py:127: UserWarning: __floordiv__ is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
@@ -556,7 +571,7 @@ torchvision rcnn models.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Get 9 valid boxes
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 58.922 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes 2.363 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 34b2bcc49..94386b046 100644
--- a/docs/how_to/deploy_models/deploy_prequantized.html
+++ b/docs/how_to/deploy_models/deploy_prequantized.html
@@ -453,10 +453,8 @@ 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]
- 25%|##5 | 3.44M/13.6M [00:00<00:00, 35.6MB/s]
- 59%|#####9 | 8.01M/13.6M [00:00<00:00, 42.8MB/s]
- 98%|#########7| 13.3M/13.6M [00:00<00:00, 48.3MB/s]
-100%|##########| 13.6M/13.6M [00:00<00:00, 46.7MB/s]
+ 63%|######3 | 8.56M/13.6M [00:00<00:00, 89.8MB/s]
+100%|##########| 13.6M/13.6M [00:00<00:00, 107MB/s]
</pre></div>
</div>
</div>
@@ -545,7 +543,7 @@ 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)
- 90.2597 90.2117 91.6938 90.0894 0.2076
+ 90.6415 90.5647 93.9084 90.2142 0.4663
</pre></div>
</div>
<div class="admonition note">
@@ -584,7 +582,7 @@ This includes support for the VNNI 8 bit dot product instruction (CascadeLake or
<div class="section" id="deploy-a-quantized-tflite-model">
<h2>Deploy a quantized TFLite Model<a class="headerlink" href="#deploy-a-quantized-tflite-model" title="Permalink to this headline">¶</a></h2>
<p>TODO</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 6.321 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 7.363 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 2664bb515..2b32ada4e 100644
--- a/docs/how_to/deploy_models/deploy_prequantized_tflite.html
+++ b/docs/how_to/deploy_models/deploy_prequantized_tflite.html
@@ -546,7 +546,7 @@ TFLite Top-5 labels: [387 102 386 341 349]
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 118.8775 118.7901 120.1228 118.3676 0.3213
+ 120.8385 120.7629 122.8763 120.1450 0.4634
</pre></div>
</div>
<div class="admonition note">
@@ -574,7 +574,7 @@ network for ARM CPU</span></a>.</p></li>
</ul>
</div></blockquote>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 52.980 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 54.209 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 20403c327..99b44d5f7 100644
--- a/docs/how_to/deploy_models/deploy_quantized.html
+++ b/docs/how_to/deploy_models/deploy_quantized.html
@@ -485,7 +485,7 @@ for calibration. But the accuracy might be impacted.</p>
DeprecationWarning,
</pre></div>
</div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 12.239 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 14.848 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 ad0aba03e..286fb1c22 100644
--- a/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
+++ b/docs/how_to/deploy_models/deploy_ssd_gluoncv.html
@@ -417,22 +417,22 @@ to your device.</p>
Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/ssd_512_resnet50_v1_voc-9c8b225a.zip...
0%| | 0/132723 [00:00<?, ?KB/s]
- 5%|5 | 6973/132723 [00:00<00:01, 69713.78KB/s]
- 12%|#1 | 15733/132723 [00:00<00:01, 80225.91KB/s]
- 18%|#8 | 24531/132723 [00:00<00:01, 83761.96KB/s]
- 25%|##4 | 32908/132723 [00:00<00:01, 74940.47KB/s]
- 31%|###1 | 41510/132723 [00:00<00:01, 78654.23KB/s]
- 38%|###7 | 50255/132723 [00:00<00:01, 81498.05KB/s]
- 45%|####4 | 59069/132723 [00:00<00:00, 83597.40KB/s]
- 51%|#####1 | 67801/132723 [00:00<00:00, 84754.52KB/s]
- 58%|#####7 | 76642/132723 [00:00<00:00, 85870.72KB/s]
- 64%|######4 | 85434/132723 [00:01<00:00, 86494.22KB/s]
- 71%|####### | 94197/132723 [00:01<00:00, 86836.33KB/s]
- 78%|#######7 | 102965/132723 [00:01<00:00, 87087.75KB/s]
- 84%|########4 | 111745/132723 [00:01<00:00, 87297.65KB/s]
- 91%|######### | 120484/132723 [00:01<00:00, 87288.26KB/s]
- 97%|#########7| 129354/132723 [00:01<00:00, 87704.11KB/s]
-100%|##########| 132723/132723 [00:01<00:00, 84515.06KB/s]
+ 4%|4 | 5752/132723 [00:00<00:02, 57511.83KB/s]
+ 11%|# | 14438/132723 [00:00<00:01, 74770.40KB/s]
+ 17%|#7 | 23085/132723 [00:00<00:01, 80107.77KB/s]
+ 24%|##3 | 31776/132723 [00:00<00:01, 82789.62KB/s]
+ 30%|### | 40277/132723 [00:00<00:01, 83577.78KB/s]
+ 37%|###6 | 48910/132723 [00:00<00:00, 84510.00KB/s]
+ 43%|####3 | 57575/132723 [00:00<00:00, 85207.36KB/s]
+ 50%|####9 | 66323/132723 [00:00<00:00, 85929.18KB/s]
+ 56%|#####6 | 74971/132723 [00:00<00:00, 86099.34KB/s]
+ 63%|######3 | 83688/132723 [00:01<00:00, 86427.33KB/s]
+ 70%|######9 | 92421/132723 [00:01<00:00, 86701.51KB/s]
+ 76%|#######6 | 101095/132723 [00:01<00:00, 86710.41KB/s]
+ 83%|########2 | 109767/132723 [00:01<00:00, 86476.08KB/s]
+ 89%|########9 | 118444/132723 [00:01<00:00, 86562.60KB/s]
+ 96%|#########5| 127106/132723 [00:01<00:00, 86578.66KB/s]
+100%|##########| 132723/132723 [00:01<00:00, 84697.10KB/s]
</pre></div>
</div>
<p>Create TVM runtime and do inference
@@ -475,7 +475,7 @@ Downloading /workspace/.mxnet/models/ssd_512_resnet50_v1_voc-9c8b225a.zip from h
<span class="n">plt</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" srcset="../../_images/sphx_glr_deploy_ssd_gluoncv_001.png" alt="deploy ssd gluoncv" class = "sphx-glr-single-img"/><p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 17.561 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 19.340 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 b63f72266..dbcf0eb23 100644
--- a/docs/how_to/deploy_models/sg_execution_times.html
+++ b/docs/how_to/deploy_models/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-deploy-models-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>10:17.402</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
+<p><strong>10:28.147</strong> total execution time for <strong>how_to_deploy_models</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 86%" />
@@ -312,31 +312,31 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_object_detection_pytorch.html#sphx-glr-how-to-deploy-models-deploy-object-detection-pytorch-py"><span class="std std-ref">Compile PyTorch Object Detection Models</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_object_detection_pytorch.py</span></code>)</p></td>
-<td><p>02:58.922</p></td>
+<td><p>03:02.363</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>02:17.561</p></td>
+<td><p>02:19.340</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_prequantized_tflite.html#sphx-glr-how-to-deploy-models-deploy-prequantized-tflite-py"><span class="std std-ref">Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_prequantized_tflite.py</span></code>)</p></td>
-<td><p>01:52.980</p></td>
+<td><p>01:54.209</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>01:12.239</p></td>
+<td><p>01:14.848</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>01:06.321</p></td>
+<td><p>01:07.363</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>00:27.917</p></td>
+<td><p>00:28.312</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>00:21.456</p></td>
+<td><p>00:21.707</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 2d39b060c..dfeada02d 100644
--- a/docs/how_to/extend_tvm/bring_your_own_datatypes.html
+++ b/docs/how_to/extend_tvm/bring_your_own_datatypes.html
@@ -585,7 +585,7 @@ In this alpha state of the Bring Your Own Datatypes framework, we have not imple
<span class="n">module</span><span class="p">,</span> <a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">params</span></a> <span class="o">=</span> <span class="n">get_mobilenet</span><span class="p">()</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Downloading /workspace/.mxnet/models/mobilenet0.25-9f83e440.zipc0ce8fef-9889-4a91-a65b-f0fd93e25599 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.zip6649b730-1211-4ad2-b2c4-4c615777e39e 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 2d0c97b85..b50b62b33 100644
--- a/docs/how_to/extend_tvm/sg_execution_times.html
+++ b/docs/how_to/extend_tvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-extend-tvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:39.337</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
+<p><strong>00:40.567</strong> total execution time for <strong>how_to_extend_tvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,15 +312,15 @@
</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>00:36.224</p></td>
+<td><p>00:37.292</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>00:02.194</p></td>
+<td><p>00:02.320</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>00:00.913</p></td>
+<td><p>00:00.948</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 719a279ac..b69ac182f 100644
--- a/docs/how_to/extend_tvm/use_pass_instrument.html
+++ b/docs/how_to/extend_tvm/use_pass_instrument.html
@@ -488,10 +488,10 @@ profile the execution time of each passes.</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6844us [6844us] (45.78%; 45.78%)
-FoldScaleAxis: 8106us [6us] (54.22%; 54.22%)
- FoldConstant: 8100us [1620us] (54.18%; 99.93%)
- InferType: 6480us [6480us] (43.34%; 80.00%)
+InferType: 7056us [7056us] (45.72%; 45.72%)
+FoldScaleAxis: 8379us [6us] (54.28%; 54.28%)
+ FoldConstant: 8373us [1625us] (54.24%; 99.93%)
+ InferType: 6748us [6748us] (43.72%; 80.60%)
</pre></div>
</div>
</div>
@@ -513,10 +513,10 @@ Refer to following sections and <a class="reference internal" href="../../refere
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Printing results of timing profile...
-InferType: 6564us [6564us] (44.86%; 44.86%)
-FoldScaleAxis: 8070us [5us] (55.14%; 55.14%)
- FoldConstant: 8065us [1632us] (55.11%; 99.94%)
- InferType: 6432us [6432us] (43.96%; 79.76%)
+InferType: 6822us [6822us] (45.19%; 45.19%)
+FoldScaleAxis: 8273us [7us] (54.81%; 54.81%)
+ FoldConstant: 8266us [1667us] (54.76%; 99.92%)
+ InferType: 6599us [6599us] (43.72%; 79.83%)
</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 fadde5b94..25b3b4752 100644
--- a/docs/how_to/optimize_operators/opt_conv_cuda.html
+++ b/docs/how_to/optimize_operators/opt_conv_cuda.html
@@ -537,7 +537,7 @@ latency of convolution.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Convolution: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">*</span> <span cl [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 51.593448 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Convolution: 54.169477 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 11c897d28..9e1801e14 100644
--- a/docs/how_to/optimize_operators/opt_conv_tensorcore.html
+++ b/docs/how_to/optimize_operators/opt_conv_tensorcore.html
@@ -879,7 +879,7 @@ be able to run on our build server</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"conv2d with tensor core: </span><span class="si">%f</span><span class="s2"> ms"</span> <span class="o">%</span> <span class="p">(</span><span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">w</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span> <span class="o">* [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 9.858491 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>conv2d with tensor core: 8.177830 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 c55ba88f5..12b2506b8 100644
--- a/docs/how_to/optimize_operators/opt_gemm.html
+++ b/docs/how_to/optimize_operators/opt_gemm.html
@@ -434,8 +434,8 @@ Then we write a baseline implementation, the simplest way to write a matrix mult
<span class="nb">print</span><span class="p">(</span><span class="s2">"Baseline: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.018503
-Baseline: 3.387383
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Numpy running time: 0.019089
+Baseline: 3.440015
</pre></div>
</div>
<p>In TVM, we can always inspect lower level IR to debug or optimize our schedule.
@@ -495,7 +495,7 @@ fill 32 * 32 * sizeof(float) which is 4KB in the cache whose total size is 32KB
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt1: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.303339
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt1: 0.294212
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -562,7 +562,7 @@ vastly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt2: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.337359
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt2: 0.332334
</pre></div>
</div>
<p>Here is the generated IR after vectorization.</p>
@@ -623,7 +623,7 @@ the access pattern for A matrix is more cache friendly.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt3: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118771
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt3: 0.118769
</pre></div>
</div>
<p>Here is the generated IR after loop permutation.</p>
@@ -706,7 +706,7 @@ flattening.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt4: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.112118
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt4: 0.110636
</pre></div>
</div>
<p>Here is the generated IR after array packing.</p>
@@ -792,7 +792,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt5: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">evaluator</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span><span class="o">.</span><span class="n">mean</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111604
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt5: 0.111732
</pre></div>
</div>
<p>Here is the generated IR after blocking.</p>
@@ -882,7 +882,7 @@ write to C when all the block results are ready.</p>
<span class="nb">print</span><span class="p">(</span><span class="s2">"Opt6: </span><span class="si">%f</span><span class="s2">"</span> <span class="o">%</span> <span class="n">opt6_time</span><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145054
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Opt6: 0.145305
</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 dc4159ee5..f1ce2aed9 100644
--- a/docs/how_to/optimize_operators/sg_execution_times.html
+++ b/docs/how_to/optimize_operators/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-optimize-operators-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:34.318</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
+<p><strong>00:34.534</strong> total execution time for <strong>how_to_optimize_operators</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="opt_gemm.html#sphx-glr-how-to-optimize-operators-opt-gemm-py"><span class="std std-ref">How to optimize GEMM on CPU</span></a> (<code class="docutils literal notranslate"><span class="pre">opt_gemm.py</span></code>)</p></td>
-<td><p>00:32.088</p></td>
+<td><p>00:32.231</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>00:01.245</p></td>
+<td><p>00:01.260</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>00:00.984</p></td>
+<td><p>00:01.044</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 9bf338618..3f7b007e3 100644
--- a/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
+++ b/docs/how_to/tune_with_autoscheduler/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autoscheduler-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>05:23.619</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
+<p><strong>05:12.383</strong> total execution time for <strong>how_to_tune_with_autoscheduler</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -312,27 +312,27 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_layer_cuda.html#sphx-glr-how-to-tune-with-autoscheduler-tune-conv2d-layer-cuda-py"><span class="std std-ref">Auto-scheduling a Convolution Layer for GPU</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_layer_cuda.py</span></code>)</p></td>
-<td><p>02:47.429</p></td>
+<td><p>02:35.043</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>01:19.686</p></td>
+<td><p>01:19.835</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>00:42.851</p></td>
+<td><p>00:42.890</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_sparse_x86.html#sphx-glr-how-to-tune-with-autoscheduler-tune-sparse-x86-py"><span class="std std-ref">Auto-scheduling Sparse Matrix Multiplication on CPU with Custom Sketch Rule</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_sparse_x86.py</span></code>)</p></td>
-<td><p>00:16.787</p></td>
+<td><p>00:17.751</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>00:08.493</p></td>
+<td><p>00:08.536</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>00:08.372</p></td>
+<td><p>00:08.329</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 ab70b2c50..c8ceaebe2 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
@@ -451,9 +451,6 @@ file and apply it.</p>
<span class="k">del</span> <span class="n">measure_ctx</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>.T
-</pre></div>
-</div>
<p>We can lower the schedule to see the IR after auto-scheduling.
The auto-scheduler correctly performs optimizations including multi-level tiling,
cooperative fetching, unrolling and operator fusion.</p>
@@ -470,293 +467,684 @@ cooperative fetching, unrolling and operator fusion.</p>
compute: Buffer(compute_2: Pointer(float32), float32, [25088], [])}
buffer_map = {data_1: data, kernel_1: kernel, bias_1: bias, compute_1: compute}
preflattened_buffer_map = {data_1: data_3: Buffer(data_2, float32, [1, 512, 7, 7], []), kernel_1: kernel_3: Buffer(kernel_2, float32, [512, 512, 3, 3], []), bias_1: bias_3: Buffer(bias_2, float32, [1, 512, 1, 1], []), compute_1: compute_3: Buffer(compute_2, float32, [1, 512, 7, 7], [])} {
- attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 32;
- allocate(conv2d_nchw: Pointer(local float32), float32, [16]), storage_scope = local;
- allocate(pad_temp.shared: Pointer(shared float32), float32, [1296]), storage_scope = shared;
- allocate(kernel.shared: Pointer(shared float32), float32, [2304]), storage_scope = shared;
- attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- conv2d_nchw_1: Buffer(conv2d_nchw, float32, [16], [], scope="local", align=16)[0] = 0f32
- conv2d_nchw_1[4] = 0f32
- conv2d_nchw_1[8] = 0f32
- conv2d_nchw_1[12] = 0f32
+ attr [IterVar(blockIdx.x: int32, (nullptr), "ThreadIndex", "blockIdx.x")] "thread_extent" = 28;
+ allocate(conv2d_nchw: Pointer(local float32), float32, [7]), storage_scope = local;
+ allocate(pad_temp.shared: Pointer(shared float32), float32, [216]), storage_scope = shared;
+ allocate(kernel.shared: Pointer(shared float32), float32, [9216]), storage_scope = shared;
+ attr [IterVar(threadIdx.x: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128 {
+ conv2d_nchw_1: Buffer(conv2d_nchw, float32, [1], [], scope="local", align=4)[0] = 0f32
conv2d_nchw_1[1] = 0f32
- conv2d_nchw_1[5] = 0f32
- conv2d_nchw_1[9] = 0f32
- conv2d_nchw_1[13] = 0f32
conv2d_nchw_1[2] = 0f32
- conv2d_nchw_1[6] = 0f32
- conv2d_nchw_1[10] = 0f32
- conv2d_nchw_1[14] = 0f32
conv2d_nchw_1[3] = 0f32
- conv2d_nchw_1[7] = 0f32
- conv2d_nchw_1[11] = 0f32
- conv2d_nchw_1[15] = 0f32
- for (rc.outer.outer: int32, 0, 32) {
- let cse_var_1: int32 = (rc.outer.outer*784)
+ conv2d_nchw_1[4] = 0f32
+ conv2d_nchw_1[5] = 0f32
+ conv2d_nchw_1[6] = 0f32
+ for (rc.outer.outer: int32, 0, 64) {
+ let cse_var_1: int32 = (rc.outer.outer*72)
{
- attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- pad_temp.shared_1: Buffer(pad_temp.shared, float32, [1296], [], scope="shared")[(threadIdx.x_1*16)] = @tir.if_then_else(((((9 <= floormod((threadIdx.x_1*16), 81)) && (floormod((threadIdx.x_1*16), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv((threadIdx.x_1*16), 81)*49)) + (floordiv(floormod((threadIdx.x_1*16), 81), 9)*7)) + floormod((threadIdx.x_1*7), 9) [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 1)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 1), 81)) && (floormod(((threadIdx.x_1*16) + 1), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 1), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 1), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 2)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 2), 81)) && (floormod(((threadIdx.x_1*16) + 2), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 2), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 2), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 3)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 3), 81)) && (floormod(((threadIdx.x_1*16) + 3), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 3), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 3), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 4)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 4), 81)) && (floormod(((threadIdx.x_1*16) + 4), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 4), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 4), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 5)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 5), 81)) && (floormod(((threadIdx.x_1*16) + 5), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 5), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 5), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 6)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 6), 81)) && (floormod(((threadIdx.x_1*16) + 6), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 6), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 6), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 7)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 7), 81)) && (floormod(((threadIdx.x_1*16) + 7), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 7), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 7), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 8)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 8), 81)) && (floormod(((threadIdx.x_1*16) + 8), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 8), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 8), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 9)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 9), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 9), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 1), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- pad_temp.shared_1[((threadIdx.x_1*16) + 10)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 10), 81)) && (floormod(((threadIdx.x_1*16) + 10), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 10), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 10), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32, dtyp [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 11)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 11), 81)) && (floormod(((threadIdx.x_1*16) + 11), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 11), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 11), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32, dtyp [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 12)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 12), 81)) && (floormod(((threadIdx.x_1*16) + 12), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 12), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 12), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32, dtyp [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 13)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 13), 81)) && (floormod(((threadIdx.x_1*16) + 13), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 13), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 13), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32, dtyp [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 14)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 14), 81)) && (floormod(((threadIdx.x_1*16) + 14), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 14), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 14), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32, dtyp [...]
- pad_temp.shared_1[((threadIdx.x_1*16) + 15)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 15), 81)) && (floormod(((threadIdx.x_1*16) + 15), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 15), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 15), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32, dtyp [...]
- }
- attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 784)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 784), 81)) && (floormod(((threadIdx.x_1*16) + 55), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 784), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 784), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 1), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 785)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 785), 81)) && (floormod(((threadIdx.x_1*16) + 56), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 785), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 785), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 786)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 786), 81)) && (floormod(((threadIdx.x_1*16) + 57), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 786), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 786), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 787)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 787), 81)) && (floormod(((threadIdx.x_1*16) + 58), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 787), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 787), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 788)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 788), 81)) && (floormod(((threadIdx.x_1*16) + 59), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 788), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 788), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 789)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 789), 81)) && (floormod(((threadIdx.x_1*16) + 60), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 789), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 789), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 790)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 790), 81)) && (floormod(((threadIdx.x_1*16) + 61), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 790), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 790), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 791)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 791), 81)) && (floormod(((threadIdx.x_1*16) + 62), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 8), 9))) && (floormod(((threadIdx.x_1*7) + 8), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 791), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 791), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 8), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 792)] = @tir.if_then_else(((((1 <= floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)) && (floormod(((threadIdx.x_1*16) + 63), 81) < 72)) && (1 <= floormod((threadIdx.x_1*7), 9))) && (floormod((threadIdx.x_1*7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 792), 81)*49)) + (floormod((floordiv((threadIdx.x_1*16), 9) + 7), 9)*7)) + floormod((threadIdx.x_1*7), 9)) - 8)], 0f32, dtype=float32)
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 793)] = @tir.if_then_else(((((1 <= floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)) && (floormod(((threadIdx.x_1*16) + 64), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 1), 9))) && (floormod(((threadIdx.x_1*7) + 1), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 793), 81)*49)) + (floormod((floordiv(((threadIdx.x_1*16) + 784), 9) + 1), 9)*7)) + floormod(((threadIdx.x_1*7 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 794)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 794), 81)) && (floormod(((threadIdx.x_1*16) + 65), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 2), 9))) && (floormod(((threadIdx.x_1*7) + 2), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 794), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 794), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 2), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 795)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 795), 81)) && (floormod(((threadIdx.x_1*16) + 66), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 3), 9))) && (floormod(((threadIdx.x_1*7) + 3), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 795), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 795), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 3), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 796)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 796), 81)) && (floormod(((threadIdx.x_1*16) + 67), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 4), 9))) && (floormod(((threadIdx.x_1*7) + 4), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 796), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 796), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 4), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 797)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 797), 81)) && (floormod(((threadIdx.x_1*16) + 68), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 5), 9))) && (floormod(((threadIdx.x_1*7) + 5), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 797), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 797), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 5), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 798)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 798), 81)) && (floormod(((threadIdx.x_1*16) + 69), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 6), 9))) && (floormod(((threadIdx.x_1*7) + 6), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 798), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 798), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 6), 9)) - 8)], 0f32 [...]
- }
- if @tir.likely((threadIdx.x_1 < 32), dtype=bool) {
- pad_temp.shared_1[((threadIdx.x_1*16) + 799)] = @tir.if_then_else(((((9 <= floormod(((threadIdx.x_1*16) + 799), 81)) && (floormod(((threadIdx.x_1*16) + 70), 81) < 72)) && (1 <= floormod(((threadIdx.x_1*7) + 7), 9))) && (floormod(((threadIdx.x_1*7) + 7), 9) < 8)), data[((((cse_var_1 + (floordiv(((threadIdx.x_1*16) + 799), 81)*49)) + (floordiv(floormod(((threadIdx.x_1*16) + 799), 81), 9)*7)) + floormod(((threadIdx.x_1*7) + 7), 9)) - 8)], 0f32 [...]
- }
- }
- attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- kernel.shared_1: Buffer(kernel.shared, float32, [2304], [], scope="shared")[(threadIdx.x_2*24)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 1)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 2)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod((threadIdx.x_2*8), 48), 3)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 3)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 4)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 5)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 1), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 6)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 7)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 8)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 2), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 9)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 10)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 11)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 1), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 12)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 13)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 14)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 4), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 15)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 16)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 17)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 5), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 18)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 19)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 20)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 2), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- kernel.shared_1[((threadIdx.x_2*24) + 21)] = kernel[(((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- kernel.shared_1[((threadIdx.x_2*24) + 22)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- kernel.shared_1[((threadIdx.x_2*24) + 23)] = kernel[((((((blockIdx.x*73728) + (floordiv(threadIdx.x_2, 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 7), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 49 {
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1176)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1177)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1178)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 392), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1179)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1180)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1181)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 3), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1182)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1183)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1184)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 394), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1185)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1186)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1187)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 1), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1188)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1189)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1190)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 4), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1191)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1192)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1193)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floordiv(floormod(((threadIdx.x_2*8) + 397), 48), 3)*9)) + (floormod(((threadIdx.x_2*2) + 1), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1194)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1195)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1196)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv(((threadIdx.x_2*8) + 392), 3) + 2), 16)*9)) + (floormod(((threadIdx.x_2*2) + 2), 3)*3)) + 2)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1197)] = kernel[(((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3))]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1198)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 1)]
- }
- if @tir.likely((threadIdx.x_2 < 47), dtype=bool) {
- kernel.shared_1[((threadIdx.x_2*24) + 1199)] = kernel[((((((blockIdx.x*73728) + (floordiv((threadIdx.x_2 + 49), 6)*4608)) + (rc.outer.outer*144)) + (floormod((floordiv((threadIdx.x_2*8), 3) + 5), 16)*9)) + (floormod((threadIdx.x_2*2), 3)*3)) + 2)]
- }
- }
- for (ff.outer.inner: int32, 0, 2) {
- for (rc.inner: int32, 0, 16) {
- let cse_var_10: int32 = (ff.outer.inner*2)
- let cse_var_9: int32 = (cse_var_10 + 9)
- let cse_var_8: int32 = (cse_var_10 + 8)
- let cse_var_7: int32 = (cse_var_10 + 5)
- let cse_var_6: int32 = (cse_var_10 + 4)
- let cse_var_5: int32 = (cse_var_10 + 13)
- let cse_var_4: int32 = (cse_var_10 + 12)
- let cse_var_3: int32 = (cse_var_10 + 1)
- let cse_var_2: int32 = ((ff.outer.inner*288) + (rc.inner*9))
- {
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[cse_var_2]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 576)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1152)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1728)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 144)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 720)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1296)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[(((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7))]*kernel.shared_1[(cse_var_2 + 1872)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 577)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1153)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1729)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 145)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 721)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1297)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 1)]*kernel.shared_1[(cse_var_2 + 1873)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 2)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 578)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1154)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1730)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 146)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 722)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1298)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 2)]*kernel.shared_1[(cse_var_2 + 1874)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 3)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 579)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1155)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1731)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 147)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 723)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1299)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 9)]*kernel.shared_1[(cse_var_2 + 1875)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 4)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 580)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1156)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1732)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 148)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 724)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1300)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 10)]*kernel.shared_1[(cse_var_2 + 1876)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 5)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 581)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1157)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1733)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 149)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 725)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1301)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 11)]*kernel.shared_1[(cse_var_2 + 1877)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 6)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 582)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1158)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1734)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 150)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 726)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1302)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 18)]*kernel.shared_1[(cse_var_2 + 1878)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 7)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 583)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1159)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1735)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 151)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 727)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1303)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 19)]*kernel.shared_1[(cse_var_2 + 1879)]))
- conv2d_nchw_1[cse_var_10] = (conv2d_nchw_1[cse_var_10] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 8)]))
- conv2d_nchw_1[cse_var_6] = (conv2d_nchw_1[cse_var_6] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 584)]))
- conv2d_nchw_1[cse_var_8] = (conv2d_nchw_1[cse_var_8] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1160)]))
- conv2d_nchw_1[cse_var_4] = (conv2d_nchw_1[cse_var_4] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1736)]))
- conv2d_nchw_1[cse_var_3] = (conv2d_nchw_1[cse_var_3] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 152)]))
- conv2d_nchw_1[cse_var_7] = (conv2d_nchw_1[cse_var_7] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 728)]))
- conv2d_nchw_1[cse_var_9] = (conv2d_nchw_1[cse_var_9] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1304)]))
- conv2d_nchw_1[cse_var_5] = (conv2d_nchw_1[cse_var_5] + (pad_temp.shared_1[((((rc.inner*81) + (floordiv(threadIdx.x, 7)*9)) + floormod(threadIdx.x, 7)) + 20)]*kernel.shared_1[(cse_var_2 + 1880)]))
- }
- }
+ attr [IterVar(threadIdx.x_1: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ pad_temp.shared_1: Buffer(pad_temp.shared, float32, [216], [], scope="shared")[threadIdx.x_1] = @tir.if_then_else(((((3 <= floormod(threadIdx.x_1, 27)) && (floormod(threadIdx.x_1, 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)))) && ((floormod(blockIdx.x, 7) + floormod(threadIdx.x_1, 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv(threadIdx.x_1, 27)*49)) + (floordiv(floormod(threadIdx.x_1, 27), 3)*7)) [...]
+ attr [IterVar(threadIdx.x_1, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ if @tir.likely((threadIdx.x_1 < 88), dtype=bool) {
+ pad_temp.shared_1[(threadIdx.x_1 + 128)] = @tir.if_then_else(((((3 <= floormod((threadIdx.x_1 + 128), 27)) && (floormod((threadIdx.x_1 + 20), 27) < 24)) && (1 <= (floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)))) && ((floormod(blockIdx.x, 7) + floormod((threadIdx.x_1 + 2), 3)) < 8)), data[((((((rc.outer.outer*392) + (floordiv((threadIdx.x_1 + 128), 27)*49)) + (floordiv(floormod((threadIdx.x_1 + 20), 27), 3)*7)) + floormod(blockIdx [...]
}
+ attr [IterVar(threadIdx.x_2: int32, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1: Buffer(kernel.shared, float32, [9216], [], scope="shared")[threadIdx.x_2] = kernel[((((floordiv(blockIdx.x, 7)*589824) + (floordiv(threadIdx.x_2, 72)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 128)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 16), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 56), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 256)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 32), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 112), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 384)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 48), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 168), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 512)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 64), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 224), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 640)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 80), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 280), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 768)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 96), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 336), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 896)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 112), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 392), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1024)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 128), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 448), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1152)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 73728)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1280)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 160), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 560), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1408)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 176), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 616), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1536)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 192), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 672), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1664)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 208), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 728), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1792)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 224), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 784), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 1920)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 240), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 840), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2048)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 256), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 896), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2176)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 272), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 952), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2304)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 147456)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2432)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 304), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1064), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2560)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 320), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1120), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2688)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 336), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1176), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2816)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 352), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1232), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 2944)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 368), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1288), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3072)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 384), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1344), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3200)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 400), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1400), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3328)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 416), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1456), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3456)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 221184)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3584)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 448), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1568), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3712)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 464), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1624), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3840)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 480), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1680), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 3968)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 496), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1736), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4096)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 512), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1792), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4224)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 528), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1848), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4352)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 544), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1904), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4480)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 560), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 1960), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4608)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 294912)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4736)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 592), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2072), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4864)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 608), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2128), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 4992)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 624), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2184), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5120)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 640), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2240), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5248)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 656), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2296), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5376)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 672), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2352), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5504)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 688), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2408), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5632)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 704), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2464), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5760)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 368640)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 5888)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 736), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2576), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6016)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 752), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2632), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6144)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 768), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2688), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6272)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 784), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2744), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6400)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 800), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2800), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6528)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 816), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2856), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6656)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 832), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2912), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6784)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 848), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 2968), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 6912)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 442368)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7040)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 880), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3080), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7168)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 896), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3136), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7296)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 912), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3192), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7424)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 928), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3248), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7552)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 944), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3304), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7680)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 960), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3360), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7808)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 976), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3416), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 7936)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 992), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3472), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8064)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv(floordiv(threadIdx.x_2, 8), 9)*4608)) + cse_var_1) + floormod(threadIdx.x_2, 72)) + 516096)]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8192)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1024), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3584), 72), 9)*9)) + floormod((threadIdx.x_2 + 2), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8320)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1040), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3640), 72), 9)*9)) + floormod((threadIdx.x_2 + 4), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8448)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1056), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3696), 72), 9)*9)) + floormod((threadIdx.x_2 + 6), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8576)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1072), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3752), 72), 9)*9)) + floormod((threadIdx.x_2 + 8), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8704)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1088), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3808), 72), 9)*9)) + floormod((threadIdx.x_2 + 1), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8832)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1104), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3864), 72), 9)*9)) + floormod((threadIdx.x_2 + 3), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 8960)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1120), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3920), 72), 9)*9)) + floormod((threadIdx.x_2 + 5), 9))]
+ attr [IterVar(threadIdx.x_2, (nullptr), "ThreadIndex", "threadIdx.x")] "thread_extent" = 128;
+ kernel.shared_1[(threadIdx.x_2 + 9088)] = kernel[(((((floordiv(blockIdx.x, 7)*589824) + (floordiv((floordiv(threadIdx.x_2, 8) + 1136), 9)*4608)) + cse_var_1) + (floordiv(floormod((threadIdx.x_2 + 3976), 72), 9)*9)) + floormod((threadIdx.x_2 + 7), 9))]
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[0]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[3]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[6]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[9]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[12]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[15]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[18]*kernel.shared_1[(threadIdx.x*72)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[1]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 1)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[2]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 2)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[27]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 9)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[28]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 10)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[29]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 11)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[3]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 3)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[4]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 4)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[5]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 5)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[30]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 12)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[31]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 13)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[32]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 14)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[6]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[9]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[12]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[15]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[18]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[21]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[24]*kernel.shared_1[((threadIdx.x*72) + 6)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[7]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[10]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[13]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[16]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[19]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[22]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[25]*kernel.shared_1[((threadIdx.x*72) + 7)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[8]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[11]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[14]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[17]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[20]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[23]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[26]*kernel.shared_1[((threadIdx.x*72) + 8)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[33]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[36]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[39]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[42]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[45]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[48]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[51]*kernel.shared_1[((threadIdx.x*72) + 15)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[34]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[37]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[40]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[43]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[46]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[49]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[52]*kernel.shared_1[((threadIdx.x*72) + 16)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[35]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[38]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[41]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[44]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[47]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[50]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[53]*kernel.shared_1[((threadIdx.x*72) + 17)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[54]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 18)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[55]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 19)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[56]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 20)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[81]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 27)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[82]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 28)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[83]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 29)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[57]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 21)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[58]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 22)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[59]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 23)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[84]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 30)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[85]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 31)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[86]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 32)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[60]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[63]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[66]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[69]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[72]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[75]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[78]*kernel.shared_1[((threadIdx.x*72) + 24)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[61]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[64]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[67]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[70]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[73]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[76]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[79]*kernel.shared_1[((threadIdx.x*72) + 25)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[62]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[65]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[68]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[71]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[74]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[77]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[80]*kernel.shared_1[((threadIdx.x*72) + 26)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[87]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[90]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[93]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[96]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[99]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[102]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[105]*kernel.shared_1[((threadIdx.x*72) + 33)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[88]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[91]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[94]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[97]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[100]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[103]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[106]*kernel.shared_1[((threadIdx.x*72) + 34)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[89]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[92]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[95]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[98]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[101]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[104]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[107]*kernel.shared_1[((threadIdx.x*72) + 35)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[108]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 36)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[109]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 37)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[110]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 38)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[135]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 45)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[136]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 46)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[137]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 47)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[111]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 39)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[112]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 40)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[113]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 41)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[138]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 48)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[139]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 49)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[140]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 50)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[114]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[117]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[120]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[123]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[126]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[129]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[132]*kernel.shared_1[((threadIdx.x*72) + 42)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[115]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[118]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[121]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[124]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[127]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[130]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[133]*kernel.shared_1[((threadIdx.x*72) + 43)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[116]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[119]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[122]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[125]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[128]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[131]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[134]*kernel.shared_1[((threadIdx.x*72) + 44)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[141]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[144]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[147]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[150]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[153]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[156]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[159]*kernel.shared_1[((threadIdx.x*72) + 51)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[142]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[145]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[148]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[151]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[154]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[157]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[160]*kernel.shared_1[((threadIdx.x*72) + 52)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[143]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[146]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[149]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[152]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[155]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[158]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[161]*kernel.shared_1[((threadIdx.x*72) + 53)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[162]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 54)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[163]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 55)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[164]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 56)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[189]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 63)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[190]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 64)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[191]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 65)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[165]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 57)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[166]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 58)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[167]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 59)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[192]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 66)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[193]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 67)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[194]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 68)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[168]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[171]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[174]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[177]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[180]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[183]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[186]*kernel.shared_1[((threadIdx.x*72) + 60)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[169]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[172]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[175]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[178]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[181]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[184]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[187]*kernel.shared_1[((threadIdx.x*72) + 61)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[170]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[173]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[176]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[179]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[182]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[185]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[188]*kernel.shared_1[((threadIdx.x*72) + 62)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[195]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[198]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[201]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[204]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[207]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[210]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[213]*kernel.shared_1[((threadIdx.x*72) + 69)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[196]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[199]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[202]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[205]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[208]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[211]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[214]*kernel.shared_1[((threadIdx.x*72) + 70)]))
+ conv2d_nchw_1[0] = (conv2d_nchw_1[0] + (pad_temp.shared_1[197]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[1] = (conv2d_nchw_1[1] + (pad_temp.shared_1[200]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[2] = (conv2d_nchw_1[2] + (pad_temp.shared_1[203]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[3] = (conv2d_nchw_1[3] + (pad_temp.shared_1[206]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[4] = (conv2d_nchw_1[4] + (pad_temp.shared_1[209]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[5] = (conv2d_nchw_1[5] + (pad_temp.shared_1[212]*kernel.shared_1[((threadIdx.x*72) + 71)]))
+ conv2d_nchw_1[6] = (conv2d_nchw_1[6] + (pad_temp.shared_1[215]*kernel.shared_1[((threadIdx.x*72) + 71)]))
}
}
- for (i1.inner: int32, 0, 4) {
- compute[(((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x)] = max((conv2d_nchw_1[i1.inner] + bias[((blockIdx.x*16) + i1.inner)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 196)] = max((conv2d_nchw_1[(i1.inner + 4)] + bias[(((blockIdx.x*16) + i1.inner) + 4)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 392)] = max((conv2d_nchw_1[(i1.inner + 8)] + bias[(((blockIdx.x*16) + i1.inner) + 8)]), 0f32)
- compute[((((blockIdx.x*784) + (i1.inner*49)) + threadIdx.x) + 588)] = max((conv2d_nchw_1[(i1.inner + 12)] + bias[(((blockIdx.x*16) + i1.inner) + 12)]), 0f32)
- }
+ compute[(((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7))] = max((conv2d_nchw_1[0] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 7)] = max((conv2d_nchw_1[1] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 14)] = max((conv2d_nchw_1[2] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 21)] = max((conv2d_nchw_1[3] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 28)] = max((conv2d_nchw_1[4] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 35)] = max((conv2d_nchw_1[5] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
+ compute[((((floordiv(blockIdx.x, 7)*6272) + (threadIdx.x*49)) + floormod(blockIdx.x, 7)) + 42)] = max((conv2d_nchw_1[6] + bias[((floordiv(blockIdx.x, 7)*128) + threadIdx.x)]), 0f32)
}
}
</pre></div>
@@ -792,7 +1180,7 @@ 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: 0.294 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 0.218 ms
</pre></div>
</div>
</div>
@@ -821,36 +1209,36 @@ conv2d_nchw_nn_o_i, conv2d_nchw_nn_i = s[conv2d_nchw].split(conv2d_nchw_nn, fact
conv2d_nchw_nn_o_o_i, conv2d_nchw_nn_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_i, factor=1)
conv2d_nchw_nn_o_o_o_i, conv2d_nchw_nn_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_i, factor=1)
conv2d_nchw_nn_o_o_o_o, conv2d_nchw_nn_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_nn_o_o_o_i, factor=1)
-conv2d_nchw_ff_o_i, conv2d_nchw_ff_i = s[conv2d_nchw].split(conv2d_nchw_ff, factor=2)
-conv2d_nchw_ff_o_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=1)
-conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=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=128)
+conv2d_nchw_ff_o_o_o_o, conv2d_nchw_ff_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_ff_o_o_o_i, factor=1)
conv2d_nchw_yy_o_i, conv2d_nchw_yy_i = s[conv2d_nchw].split(conv2d_nchw_yy, factor=1)
conv2d_nchw_yy_o_o_i, conv2d_nchw_yy_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_i, factor=1)
-conv2d_nchw_yy_o_o_o_i, conv2d_nchw_yy_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_i, factor=7)
-conv2d_nchw_yy_o_o_o_o, conv2d_nchw_yy_o_o_o_i = s[conv2d_nchw].split(conv2d_nchw_yy_o_o_o_i, factor=1)
+conv2d_nchw_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=7)
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=1)
-conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=3)
-conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=1)
+conv2d_nchw_rc_o_i, conv2d_nchw_rc_i = s[conv2d_nchw].split(conv2d_nchw_rc, factor=2)
+conv2d_nchw_rc_o_o, conv2d_nchw_rc_o_i = s[conv2d_nchw].split(conv2d_nchw_rc_o_i, factor=4)
+conv2d_nchw_ry_o_i, conv2d_nchw_ry_i = s[conv2d_nchw].split(conv2d_nchw_ry, factor=1)
+conv2d_nchw_ry_o_o, conv2d_nchw_ry_o_i = s[conv2d_nchw].split(conv2d_nchw_ry_o_i, factor=3)
conv2d_nchw_rx_o_i, conv2d_nchw_rx_i = s[conv2d_nchw].split(conv2d_nchw_rx, factor=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=4)
-compute_i1_o_o_i, compute_i1_o_i = s[compute].split(compute_i1_o_i, factor=1)
-compute_i1_o_o_o, compute_i1_o_o_i = s[compute].split(compute_i1_o_o_i, factor=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=128)
+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_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=1)
+compute_i2_o_o_i, compute_i2_o_i = s[compute].split(compute_i2_o_i, factor=1)
+compute_i2_o_o_o, compute_i2_o_o_i = s[compute].split(compute_i2_o_o_i, factor=7)
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)
@@ -868,14 +1256,14 @@ s[compute].bind(compute_i0_o_o_i_i1_o_o_i_fused_i2_o_o_i_fused_i3_o_o_i_fused, t
compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused = s[compute].fuse(compute_i0_o_i, compute_i1_o_i, compute_i2_o_i, compute_i3_o_i)
s[compute].bind(compute_i0_o_i_i1_o_i_fused_i2_o_i_fused_i3_o_i_fused, te.thread_axis("threadIdx.x"))
kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused = s[kernel_shared].fuse(kernel_shared_ax0, kernel_shared_ax1, kernel_shared_ax2, kernel_shared_ax3)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=24)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[kernel_shared].vectorize(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[kernel_shared].split(kernel_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=128)
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=16)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused, factor=1)
s[pad_temp_shared].vectorize(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_i)
-pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=49)
+pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_o, pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i = s[pad_temp_shared].split(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o, factor=128)
s[pad_temp_shared].bind(pad_temp_shared_ax0_ax1_fused_ax2_fused_ax3_fused_o_i, te.thread_axis("threadIdx.x"))
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "auto_unroll_max_step", 512)
s[conv2d_nchw].pragma(conv2d_nchw_nn_o_o_o_o, "unroll_explicit", True)
@@ -895,272 +1283,608 @@ CUDA source code:
#define int64_t long long
#define uint64_t unsigned long long
#endif
-extern "C" __global__ void __launch_bounds__(49) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
- float conv2d_nchw[16];
- __shared__ float pad_temp_shared[1296];
- __shared__ float kernel_shared[2304];
+extern "C" __global__ void __launch_bounds__(128) default_function_kernel0(float* __restrict__ data, float* __restrict__ kernel, float* __restrict__ compute, float* __restrict__ bias) {
+ float conv2d_nchw[7];
+ __shared__ float pad_temp_shared[216];
+ __shared__ float kernel_shared[9216];
conv2d_nchw[0] = 0.000000e+00f;
- conv2d_nchw[4] = 0.000000e+00f;
- conv2d_nchw[8] = 0.000000e+00f;
- conv2d_nchw[12] = 0.000000e+00f;
conv2d_nchw[1] = 0.000000e+00f;
- conv2d_nchw[5] = 0.000000e+00f;
- conv2d_nchw[9] = 0.000000e+00f;
- conv2d_nchw[13] = 0.000000e+00f;
conv2d_nchw[2] = 0.000000e+00f;
- conv2d_nchw[6] = 0.000000e+00f;
- conv2d_nchw[10] = 0.000000e+00f;
- conv2d_nchw[14] = 0.000000e+00f;
conv2d_nchw[3] = 0.000000e+00f;
- conv2d_nchw[7] = 0.000000e+00f;
- conv2d_nchw[11] = 0.000000e+00f;
- conv2d_nchw[15] = 0.000000e+00f;
- for (int rc_outer_outer = 0; rc_outer_outer < 32; ++rc_outer_outer) {
+ conv2d_nchw[4] = 0.000000e+00f;
+ conv2d_nchw[5] = 0.000000e+00f;
+ conv2d_nchw[6] = 0.000000e+00f;
+ for (int rc_outer_outer = 0; rc_outer_outer < 64; ++rc_outer_outer) {
__syncthreads();
- pad_temp_shared[(((int)threadIdx.x) * 16)] = (((((9 <= ((((int)threadIdx.x) * 16) % 81)) && (((((int)threadIdx.x) * 16) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + (((((int)threadIdx.x) * 16) / 81) * 49)) + ((((((int)threadIdx.x) * 16) % 81) / 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 1)] = (((((9 <= (((((int)threadIdx.x) * 16) + 1) % 81)) && ((((((int)threadIdx.x) * 16) + 1) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 1) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 1) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 2)] = (((((9 <= (((((int)threadIdx.x) * 16) + 2) % 81)) && ((((((int)threadIdx.x) * 16) + 2) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 2) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 2) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 3)] = (((((9 <= (((((int)threadIdx.x) * 16) + 3) % 81)) && ((((((int)threadIdx.x) * 16) + 3) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 3) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 3) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 4)] = (((((9 <= (((((int)threadIdx.x) * 16) + 4) % 81)) && ((((((int)threadIdx.x) * 16) + 4) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 4) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 4) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 5)] = (((((9 <= (((((int)threadIdx.x) * 16) + 5) % 81)) && ((((((int)threadIdx.x) * 16) + 5) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 5) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 5) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 6)] = (((((9 <= (((((int)threadIdx.x) * 16) + 6) % 81)) && ((((((int)threadIdx.x) * 16) + 6) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 6) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 6) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 7)] = (((((9 <= (((((int)threadIdx.x) * 16) + 7) % 81)) && ((((((int)threadIdx.x) * 16) + 7) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 7) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 7) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 8)] = (((((9 <= (((((int)threadIdx.x) * 16) + 8) % 81)) && ((((((int)threadIdx.x) * 16) + 8) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 8) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 8) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 9)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 9) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 9) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 1) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 10)] = (((((9 <= (((((int)threadIdx.x) * 16) + 10) % 81)) && ((((((int)threadIdx.x) * 16) + 10) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 10) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 10) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 11)] = (((((9 <= (((((int)threadIdx.x) * 16) + 11) % 81)) && ((((((int)threadIdx.x) * 16) + 11) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 11) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 11) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 12)] = (((((9 <= (((((int)threadIdx.x) * 16) + 12) % 81)) && ((((((int)threadIdx.x) * 16) + 12) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 12) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 12) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 13)] = (((((9 <= (((((int)threadIdx.x) * 16) + 13) % 81)) && ((((((int)threadIdx.x) * 16) + 13) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 13) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 13) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 14)] = (((((9 <= (((((int)threadIdx.x) * 16) + 14) % 81)) && ((((((int)threadIdx.x) * 16) + 14) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 14) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 14) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- pad_temp_shared[((((int)threadIdx.x) * 16) + 15)] = (((((9 <= (((((int)threadIdx.x) * 16) + 15) % 81)) && ((((((int)threadIdx.x) * 16) + 15) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 15) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 15) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 784)] = (((((9 <= (((((int)threadIdx.x) * 16) + 55) % 81)) && ((((((int)threadIdx.x) * 16) + 55) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 784) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 55) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 785)] = (((((9 <= (((((int)threadIdx.x) * 16) + 56) % 81)) && ((((((int)threadIdx.x) * 16) + 56) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 785) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 56) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 786)] = (((((9 <= (((((int)threadIdx.x) * 16) + 57) % 81)) && ((((((int)threadIdx.x) * 16) + 57) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 786) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 57) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 787)] = (((((9 <= (((((int)threadIdx.x) * 16) + 58) % 81)) && ((((((int)threadIdx.x) * 16) + 58) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 787) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 58) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 788)] = (((((9 <= (((((int)threadIdx.x) * 16) + 59) % 81)) && ((((((int)threadIdx.x) * 16) + 59) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 788) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 59) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 789)] = (((((9 <= (((((int)threadIdx.x) * 16) + 60) % 81)) && ((((((int)threadIdx.x) * 16) + 60) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 789) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 60) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 790)] = (((((9 <= (((((int)threadIdx.x) * 16) + 61) % 81)) && ((((((int)threadIdx.x) * 16) + 61) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 790) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 61) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 791)] = (((((9 <= (((((int)threadIdx.x) * 16) + 62) % 81)) && ((((((int)threadIdx.x) * 16) + 62) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 8) % 9))) && ((((((int)threadIdx.x) * 7) + 8) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 791) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 62) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 8) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 792)] = (((((1 <= ((((((int)threadIdx.x) * 16) / 9) + 7) % 9)) && ((((((int)threadIdx.x) * 16) + 63) % 81) < 72)) && (1 <= ((((int)threadIdx.x) * 7) % 9))) && (((((int)threadIdx.x) * 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 792) / 81) * 49)) + (((((((int)threadIdx.x) * 16) / 9) + 7) % 9) * 7)) + ((((int)threadIdx.x) * 7) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 793)] = (((((1 <= (((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9)) && ((((((int)threadIdx.x) * 16) + 64) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 1) % 9))) && ((((((int)threadIdx.x) * 7) + 1) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 793) / 81) * 49)) + ((((((((int)threadIdx.x) * 16) + 784) / 9) + 1) % 9) * 7)) + (((((int)threadIdx.x) * 7) + 1) % 9)) - [...]
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 794)] = (((((9 <= (((((int)threadIdx.x) * 16) + 65) % 81)) && ((((((int)threadIdx.x) * 16) + 65) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 2) % 9))) && ((((((int)threadIdx.x) * 7) + 2) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 794) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 65) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 2) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 795)] = (((((9 <= (((((int)threadIdx.x) * 16) + 66) % 81)) && ((((((int)threadIdx.x) * 16) + 66) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 3) % 9))) && ((((((int)threadIdx.x) * 7) + 3) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 795) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 66) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 3) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 796)] = (((((9 <= (((((int)threadIdx.x) * 16) + 67) % 81)) && ((((((int)threadIdx.x) * 16) + 67) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 4) % 9))) && ((((((int)threadIdx.x) * 7) + 4) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 796) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 67) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 4) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 797)] = (((((9 <= (((((int)threadIdx.x) * 16) + 68) % 81)) && ((((((int)threadIdx.x) * 16) + 68) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 5) % 9))) && ((((((int)threadIdx.x) * 7) + 5) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 797) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 68) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 5) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 798)] = (((((9 <= (((((int)threadIdx.x) * 16) + 69) % 81)) && ((((((int)threadIdx.x) * 16) + 69) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 6) % 9))) && ((((((int)threadIdx.x) * 7) + 6) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 798) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 69) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 6) % 9)) - 8)] : 0.000000e+00f);
- }
- if (((int)threadIdx.x) < 32) {
- pad_temp_shared[((((int)threadIdx.x) * 16) + 799)] = (((((9 <= (((((int)threadIdx.x) * 16) + 70) % 81)) && ((((((int)threadIdx.x) * 16) + 70) % 81) < 72)) && (1 <= (((((int)threadIdx.x) * 7) + 7) % 9))) && ((((((int)threadIdx.x) * 7) + 7) % 9) < 8)) ? data[(((((rc_outer_outer * 784) + ((((((int)threadIdx.x) * 16) + 799) / 81) * 49)) + (((((((int)threadIdx.x) * 16) + 70) % 81) / 9) * 7)) + (((((int)threadIdx.x) * 7) + 7) % 9)) - 8)] : 0.000000e+00f);
- }
- kernel_shared[(((int)threadIdx.x) * 24)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 1)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 2)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((int)threadIdx.x) % 6) * 8) / 3) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 3)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 4)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 5)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 1) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 6)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 7)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 8)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 2) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 9)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 10)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 11)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 1) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 12)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 13)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 14)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 4) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 15)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 16)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 17)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 5) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 18)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 19)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 20)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 2) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- kernel_shared[((((int)threadIdx.x) * 24) + 21)] = kernel[(((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- kernel_shared[((((int)threadIdx.x) * 24) + 22)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- kernel_shared[((((int)threadIdx.x) * 24) + 23)] = kernel[((((((((int)blockIdx.x) * 73728) + ((((int)threadIdx.x) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) % 6) * 8) + 7) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1176)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1177)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1178)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 8) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1179)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1180)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1181)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 3) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1182)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1183)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1184)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 10) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1185)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1186)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1187)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 1) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1188)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1189)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1190)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 4) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1191)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1192)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1193)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) + 13) % 48) / 3) * 9)) + ((((((int)threadIdx.x) * 2) + 1) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1194)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1195)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1196)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + ((((((((int)threadIdx.x) * 8) + 392) / 3) + 2) & 15) * 9)) + ((((((int)threadIdx.x) * 2) + 2) % 3) * 3)) + 2)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1197)] = kernel[(((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3))];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1198)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 1)];
- }
- if (((int)threadIdx.x) < 47) {
- kernel_shared[((((int)threadIdx.x) * 24) + 1199)] = kernel[((((((((int)blockIdx.x) * 73728) + (((((int)threadIdx.x) + 49) / 6) * 4608)) + (rc_outer_outer * 144)) + (((((((int)threadIdx.x) * 8) / 3) + 5) & 15) * 9)) + (((((int)threadIdx.x) * 2) % 3) * 3)) + 2)];
+ pad_temp_shared[((int)threadIdx.x)] = (((((3 <= (((int)threadIdx.x) % 27)) && ((((int)threadIdx.x) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)))) && (((((int)blockIdx.x) % 7) + (((int)threadIdx.x) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + ((((int)threadIdx.x) / 27) * 49)) + (((((int)threadIdx.x) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + (((int)threadIdx.x) % 3)) - 8)] : 0.000000e+00f);
+ if (((int)threadIdx.x) < 88) {
+ pad_temp_shared[(((int)threadIdx.x) + 128)] = (((((3 <= ((((int)threadIdx.x) + 20) % 27)) && (((((int)threadIdx.x) + 20) % 27) < 24)) && (1 <= ((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)))) && (((((int)blockIdx.x) % 7) + ((((int)threadIdx.x) + 2) % 3)) < 8)) ? data[((((((rc_outer_outer * 392) + (((((int)threadIdx.x) + 128) / 27) * 49)) + ((((((int)threadIdx.x) + 20) % 27) / 3) * 7)) + (((int)blockIdx.x) % 7)) + ((((int)threadIdx.x) [...]
}
+ kernel_shared[((int)threadIdx.x)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 128)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 128) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 256)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 256) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 384)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 384) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 512)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 512) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 640)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 640) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 768)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 768) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 896)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 896) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1024)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1024) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1152)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 73728)];
+ kernel_shared[(((int)threadIdx.x) + 1280)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1280) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1408)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1408) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1536)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1536) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1664)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1664) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 1792)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1792) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 1920)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 1920) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2048)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2048) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2176)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2176) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2304)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 147456)];
+ kernel_shared[(((int)threadIdx.x) + 2432)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2432) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2560)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2560) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2688)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2688) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 2816)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2816) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 2944)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 2944) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3072)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3072) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3200)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3200) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3328)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3328) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3456)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 221184)];
+ kernel_shared[(((int)threadIdx.x) + 3584)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3584) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3712)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3712) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3840)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3840) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 3968)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 3968) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 4096)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4096) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4224)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4224) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4352)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4352) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4480)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4480) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4608)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 294912)];
+ kernel_shared[(((int)threadIdx.x) + 4736)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4736) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4864)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4864) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 4992)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 4992) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5120)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5120) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 5248)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5248) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5376)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5376) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5504)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5504) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5632)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5632) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 5760)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 368640)];
+ kernel_shared[(((int)threadIdx.x) + 5888)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 5888) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6016)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6016) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6144)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6144) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6272)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6272) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 6400)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6400) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6528)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6528) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6656)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6656) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6784)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 6784) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 6912)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 442368)];
+ kernel_shared[(((int)threadIdx.x) + 7040)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7040) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7168)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7168) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7296)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7296) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7424)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7424) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 7552)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7552) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7680)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7680) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7808)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7808) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 7936)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 7936) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8064)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + ((((int)threadIdx.x) / 72) * 4608)) + (rc_outer_outer * 72)) + (((int)threadIdx.x) % 72)) + 516096)];
+ kernel_shared[(((int)threadIdx.x) + 8192)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8192) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 56) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 2) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8320)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8320) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 40) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 4) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8448)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8448) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 24) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 6) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8576)] = kernel[(((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8576) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((int)threadIdx.x) + 8) % 72))];
+ kernel_shared[(((int)threadIdx.x) + 8704)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8704) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 64) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 1) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8832)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8832) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 48) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 3) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 8960)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 8960) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 32) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 5) % 9))];
+ kernel_shared[(((int)threadIdx.x) + 9088)] = kernel[((((((((int)blockIdx.x) / 7) * 589824) + (((((int)threadIdx.x) + 9088) / 72) * 4608)) + (rc_outer_outer * 72)) + ((((((int)threadIdx.x) + 16) % 72) / 9) * 9)) + ((((int)threadIdx.x) + 7) % 9))];
__syncthreads();
- 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 * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[((ff_outer_inner * 288) + (rc_inner * 9))]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 576)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1152)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1728)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 144)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 720)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1296)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[(((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7))] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1872)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 577)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1153)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1729)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 145)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 721)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1297)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 1)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1873)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 2)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 578)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1154)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1730)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 146)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 722)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1298)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 2)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1874)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 3)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 579)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1155)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1731)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 147)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 723)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1299)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 9)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1875)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 4)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 580)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1156)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1732)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 148)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 724)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1300)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 10)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1876)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 5)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 581)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1157)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1733)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 149)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 725)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1301)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 11)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1877)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 6)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 582)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1158)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1734)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 150)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 726)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1302)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 18)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1878)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 7)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 583)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1159)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1735)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 151)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 727)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1303)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 19)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1879)]));
- conv2d_nchw[(ff_outer_inner * 2)] = (conv2d_nchw[(ff_outer_inner * 2)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 8)]));
- conv2d_nchw[((ff_outer_inner * 2) + 4)] = (conv2d_nchw[((ff_outer_inner * 2) + 4)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 584)]));
- conv2d_nchw[((ff_outer_inner * 2) + 8)] = (conv2d_nchw[((ff_outer_inner * 2) + 8)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1160)]));
- conv2d_nchw[((ff_outer_inner * 2) + 12)] = (conv2d_nchw[((ff_outer_inner * 2) + 12)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1736)]));
- conv2d_nchw[((ff_outer_inner * 2) + 1)] = (conv2d_nchw[((ff_outer_inner * 2) + 1)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 152)]));
- conv2d_nchw[((ff_outer_inner * 2) + 5)] = (conv2d_nchw[((ff_outer_inner * 2) + 5)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 728)]));
- conv2d_nchw[((ff_outer_inner * 2) + 9)] = (conv2d_nchw[((ff_outer_inner * 2) + 9)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1304)]));
- conv2d_nchw[((ff_outer_inner * 2) + 13)] = (conv2d_nchw[((ff_outer_inner * 2) + 13)] + (pad_temp_shared[((((rc_inner * 81) + ((((int)threadIdx.x) / 7) * 9)) + (((int)threadIdx.x) % 7)) + 20)] * kernel_shared[(((ff_outer_inner * 288) + (rc_inner * 9)) + 1880)]));
- }
- }
- }
- for (int i1_inner = 0; i1_inner < 4; ++i1_inner) {
- compute[(((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x))] = max((conv2d_nchw[i1_inner] + bias[((((int)blockIdx.x) * 16) + i1_inner)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 196)] = max((conv2d_nchw[(i1_inner + 4)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 4)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 392)] = max((conv2d_nchw[(i1_inner + 8)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 8)]), 0.000000e+00f);
- compute[((((((int)blockIdx.x) * 784) + (i1_inner * 49)) + ((int)threadIdx.x)) + 588)] = max((conv2d_nchw[(i1_inner + 12)] + bias[(((((int)blockIdx.x) * 16) + i1_inner) + 12)]), 0.000000e+00f);
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[0] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[3] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[6] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[9] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[12] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[15] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[18] * kernel_shared[(((int)threadIdx.x) * 72)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[1] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 1)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[2] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 2)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[27] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 9)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[28] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 10)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[29] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 11)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[3] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 3)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[4] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 4)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[5] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 5)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[30] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 12)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[31] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 13)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[32] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 14)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[6] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[9] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[12] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[15] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[18] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[21] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[24] * kernel_shared[((((int)threadIdx.x) * 72) + 6)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[7] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[10] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[13] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[16] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[19] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[22] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[25] * kernel_shared[((((int)threadIdx.x) * 72) + 7)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[8] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[11] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[14] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[17] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[20] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[23] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[26] * kernel_shared[((((int)threadIdx.x) * 72) + 8)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[33] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[36] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[39] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[42] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[45] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[48] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[51] * kernel_shared[((((int)threadIdx.x) * 72) + 15)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[34] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[37] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[40] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[43] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[46] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[49] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[52] * kernel_shared[((((int)threadIdx.x) * 72) + 16)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[35] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[38] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[41] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[44] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[47] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[50] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[53] * kernel_shared[((((int)threadIdx.x) * 72) + 17)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[54] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 18)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[55] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 19)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[56] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 20)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[81] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 27)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[82] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 28)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[83] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 29)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[57] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 21)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[58] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 22)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[59] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 23)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[84] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 30)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[85] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 31)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[86] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 32)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[60] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[63] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[66] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[69] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[72] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[75] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[78] * kernel_shared[((((int)threadIdx.x) * 72) + 24)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[61] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[64] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[67] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[70] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[73] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[76] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[79] * kernel_shared[((((int)threadIdx.x) * 72) + 25)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[62] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[65] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[68] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[71] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[74] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[77] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[80] * kernel_shared[((((int)threadIdx.x) * 72) + 26)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[87] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[90] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[93] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[96] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[99] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[102] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[105] * kernel_shared[((((int)threadIdx.x) * 72) + 33)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[88] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[91] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[94] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[97] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[100] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[103] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[106] * kernel_shared[((((int)threadIdx.x) * 72) + 34)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[89] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[92] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[95] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[98] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[101] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[104] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[107] * kernel_shared[((((int)threadIdx.x) * 72) + 35)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[108] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 36)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[109] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 37)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[110] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 38)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[135] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 45)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[136] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 46)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[137] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 47)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[111] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 39)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[112] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 40)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[113] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 41)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[138] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 48)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[139] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 49)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[140] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 50)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[114] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[117] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[120] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[123] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[126] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[129] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[132] * kernel_shared[((((int)threadIdx.x) * 72) + 42)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[115] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[118] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[121] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[124] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[127] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[130] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[133] * kernel_shared[((((int)threadIdx.x) * 72) + 43)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[116] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[119] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[122] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[125] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[128] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[131] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[134] * kernel_shared[((((int)threadIdx.x) * 72) + 44)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[141] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[144] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[147] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[150] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[153] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[156] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[159] * kernel_shared[((((int)threadIdx.x) * 72) + 51)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[142] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[145] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[148] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[151] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[154] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[157] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[160] * kernel_shared[((((int)threadIdx.x) * 72) + 52)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[143] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[146] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[149] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[152] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[155] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[158] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[161] * kernel_shared[((((int)threadIdx.x) * 72) + 53)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[162] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 54)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[163] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 55)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[164] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 56)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[189] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 63)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[190] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 64)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[191] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 65)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[165] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 57)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[166] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 58)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[167] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 59)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[192] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 66)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[193] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 67)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[194] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 68)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[168] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[171] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[174] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[177] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[180] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[183] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[186] * kernel_shared[((((int)threadIdx.x) * 72) + 60)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[169] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[172] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[175] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[178] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[181] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[184] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[187] * kernel_shared[((((int)threadIdx.x) * 72) + 61)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[170] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[173] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[176] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[179] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[182] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[185] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[188] * kernel_shared[((((int)threadIdx.x) * 72) + 62)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[195] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[198] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[201] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[204] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[207] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[210] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[213] * kernel_shared[((((int)threadIdx.x) * 72) + 69)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[196] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[199] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[202] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[205] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[208] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[211] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[214] * kernel_shared[((((int)threadIdx.x) * 72) + 70)]));
+ conv2d_nchw[0] = (conv2d_nchw[0] + (pad_temp_shared[197] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[1] = (conv2d_nchw[1] + (pad_temp_shared[200] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[2] = (conv2d_nchw[2] + (pad_temp_shared[203] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[3] = (conv2d_nchw[3] + (pad_temp_shared[206] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[4] = (conv2d_nchw[4] + (pad_temp_shared[209] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[5] = (conv2d_nchw[5] + (pad_temp_shared[212] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
+ conv2d_nchw[6] = (conv2d_nchw[6] + (pad_temp_shared[215] * kernel_shared[((((int)threadIdx.x) * 72) + 71)]));
}
+ compute[((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7))] = max((conv2d_nchw[0] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 7)] = max((conv2d_nchw[1] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 14)] = max((conv2d_nchw[2] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 21)] = max((conv2d_nchw[3] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 28)] = max((conv2d_nchw[4] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 35)] = max((conv2d_nchw[5] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
+ compute[(((((((int)blockIdx.x) / 7) * 6272) + (((int)threadIdx.x) * 49)) + (((int)blockIdx.x) % 7)) + 42)] = max((conv2d_nchw[6] + bias[(((((int)blockIdx.x) / 7) * 128) + ((int)threadIdx.x))]), 0.000000e+00f);
}
</pre></div>
</div>
@@ -1196,7 +1920,7 @@ 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 47.429 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 35.043 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 ababe4f97..eaa136feb 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_cuda.html
@@ -882,7 +882,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 9.8417 9.8570 9.8785 9.7895 0.0379
+ 9.8540 9.8315 9.9087 9.8219 0.0389
</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 465840654..bacb4b733 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_network_x86.html
@@ -901,7 +901,7 @@ so we can read the log file and load the best schedules.</p>
Evaluate inference time cost...
Execution time summary:
mean (ms) median (ms) max (ms) min (ms) std (ms)
- 756.0358 755.8824 756.5194 755.7055 0.3495
+ 763.3928 763.1774 764.3128 762.6881 0.6806
</pre></div>
</div>
</div>
@@ -923,7 +923,7 @@ to learn how to use the RPC Tracker and RPC Server.
To use the RPC Tracker in auto-scheduler, replace the runner in <code class="code docutils literal notranslate"><span class="pre">TuningOptions</span></code>
with <a class="reference internal" href="../../reference/api/python/auto_scheduler.html#tvm.auto_scheduler.RPCRunner" title="tvm.auto_scheduler.RPCRunner"><code class="xref any py py-class docutils literal notranslate"><span class="pre">auto_scheduler.RPCRunner</span></code></a>.</p></li>
</ol>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.686 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 19.835 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 880207eb9..2f3ea22c6 100644
--- a/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
+++ b/docs/how_to/tune_with_autoscheduler/tune_sparse_x86.html
@@ -601,27 +601,30 @@ layout transformation, parallelization, vectorization, unrolling, and operator f
placeholder_4: Buffer(placeholder_14: Pointer(float32), float32, [65536], []),
compute: Buffer(compute_2: Pointer(float32), float32, [65536], [])}
buffer_map = {placeholder_5: placeholder, placeholder_6: placeholder_1, placeholder_7: placeholder_2, placeholder_8: placeholder_3, placeholder_9: placeholder_4, compute_1: compute}
- preflattened_buffer_map = {placeholder_5: placeholder_15: Buffer(placeholder_10, float32, [128, 256], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_8: placeholder_17: Buffer(placeholder_13, int32, [33], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
- for (i0.outer: int32, 0, 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) {
+ preflattened_buffer_map = {placeholder_8: placeholder_15: Buffer(placeholder_13, int32, [33], []), compute_1: compute_3: Buffer(compute_2, float32, [128, 512], []), placeholder_7: placeholder_16: Buffer(placeholder_12, int32, [4916], []), placeholder_5: placeholder_17: Buffer(placeholder_10, float32, [128, 256], []), placeholder_9: placeholder_18: Buffer(placeholder_14, float32, [128, 512], []), placeholder_6: placeholder_19: Buffer(placeholder_11, float32, [4916, 16, 1], [])} {
+ for (i0.outer.i1.outer.fused: int32, 0, 64) "parallel" {
+ allocate(compute_4: Pointer(global float32), float32, [1024]), storage_scope = global {
+ for (nb_j.inner: int32, 0, 2) {
+ for (i.inner.init: int32, 0, 32) {
for (j.init: int32, 0, 16) {
- compute_5: Buffer(compute_4, float32, [64], [])[(((i.outer.inner*32) + (nb_j.inner*16)) + j.init)] = 0f32
+ compute_5: Buffer(compute_4, float32, [1024], [])[(((i.inner.init*32) + (nb_j.inner*16)) + j.init)] = 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 (elem_idx: int32, 0, let cse_var_1: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner) in (placeholder_3[(cse_var_1 + 1)] - placeholder_3[cse_var_1])) {
+ for (i.inner: int32, 0, 32) {
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)))
+ let cse_var_3: int32 = ((floormod(i0.outer.i1.outer.fused, 16)*2) + nb_j.inner)
+ let cse_var_2: int32 = (((i.inner*32) + (nb_j.inner*16)) + j)
+ compute_5[cse_var_2] = (compute_5[cse_var_2] + (placeholder_1[(((placeholder_3[cse_var_3]*16) + (elem_idx*16)) + j)]*max(placeholder[(((floordiv(i0.outer.i1.outer.fused, 16)*8192) + (i.inner*256)) + placeholder_2[(placeholder_3[cse_var_3] + elem_idx)])], 0f32)))
}
}
}
}
- 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))
+ for (i0.inner: int32, 0, 32) {
+ for (i1.inner: int32, 0, 32) {
+ let cse_var_4: int32 = ((((floordiv(i0.outer.i1.outer.fused, 16)*16384) + (i0.inner*512)) + (floormod(i0.outer.i1.outer.fused, 16)*32)) + i1.inner)
+ compute[cse_var_4] = max((compute_5[((i0.inner*32) + i1.inner)] + placeholder_4[cse_var_4]), 0f32)
+ }
}
}
}
@@ -659,7 +662,7 @@ 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: 1.905 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 1.645 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 e3cbde5ff..e6e794e68 100644
--- a/docs/how_to/tune_with_autotvm/sg_execution_times.html
+++ b/docs/how_to/tune_with_autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-tune-with-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:42.911</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
+<p><strong>00:43.418</strong> total execution time for <strong>how_to_tune_with_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_conv2d_cuda.html#sphx-glr-how-to-tune-with-autotvm-tune-conv2d-cuda-py"><span class="std std-ref">Tuning High Performance Convolution on NVIDIA GPUs</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_conv2d_cuda.py</span></code>)</p></td>
-<td><p>00:42.880</p></td>
+<td><p>00:43.384</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>00:00.019</p></td>
+<td><p>00:00.021</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 8a68965cd..3970f4c25 100644
--- a/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
+++ b/docs/how_to/tune_with_autotvm/tune_conv2d_cuda.html
@@ -1145,8 +1145,8 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 4, 32]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 1, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2885496
-No: 6 GFLOPS: 96.52/96.52 result: MeasureResult(costs=(0.0023985371875,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8076894283294678, timestamp=1655777059.6730833) [('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: 0.00/96.52 result: Traceback (most recent call last):
+No: 6 GFLOPS: 42.34/42.34 result: MeasureResult(costs=(0.005467819631578948,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.647458791732788, timestamp=1655836731.6531527) [('tile_f', [-1, 1, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,3754080
+No: 7 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1269,7 +1269,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 16, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 256, 1]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6225319
-No: 8 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 8 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1392,7 +1392,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 32]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 8, 64]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,943546
-No: 9 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 9 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1515,7 +1515,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 4, 16, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 16, 32]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2868708
-No: 10 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 10 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 142, in build
res = future.result()
File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
@@ -1533,7 +1533,7 @@ No: 10 GFLOPS: 0.00/96.52 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: 0.00/96.52 result: Traceback (most recent call last):
+No: 11 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1656,7 +1656,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 2, 64]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,1042124
-No: 12 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 12 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1779,7 +1779,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 32, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 32, 16]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,10013405
-No: 13 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 13 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -1902,7 +1902,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 8, 8, 2]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 1, 7, 1]), ('tile_rc', [-1, 4, 32]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6732082
-No: 14 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 14 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2025,7 +2025,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 4, 32]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 1, 1, 1]), ('tile_rc', [-1, 4, 128]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 1)],None,7536735
-No: 15 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 15 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2148,7 +2148,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 4]), ('tile_y', [-1, 1, 1, 7]), ('tile_x', [-1, 1, 1, 7]), ('tile_rc', [-1, 128, 4]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 1, 1]), ('auto_unroll_max_step', 0), ('unroll_explicit', 0)],None,482121
-No: 16 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 16 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2271,7 +2271,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 2, 1, 16]), ('tile_y', [-1, 1, 7, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 32, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 512), ('unroll_explicit', 0)],None,2824525
-No: 17 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 17 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2394,7 +2394,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 64, 1, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 8, 8]), ('tile_ry', [-1, 1, 3]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 0)],None,4559286
-No: 18 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 18 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 588, in __call__
func, arg_info = _build_func_common(measure_input, self.runtime, **kwargs)
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 540, in _build_func_common
@@ -2517,7 +2517,7 @@ Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 871, in verify_pass
raise InstantiationError("Skipped because of invalid gpu kernel")
tvm.autotvm.task.space.InstantiationError: Skipped because of invalid gpu kernel [('tile_f', [-1, 1, 32, 16]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 512]), ('tile_ry', [-1, 3, 1]), ('tile_rx', [-1, 3, 1]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9677544
-No: 19 GFLOPS: 0.00/96.52 result: Traceback (most recent call last):
+No: 19 GFLOPS: 0.00/42.34 result: Traceback (most recent call last):
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 738, in __call__
yield remote, remote.load_module(os.path.split(build_result.filename)[1])
File "/workspace/python/tvm/autotvm/measure/measure_methods.py", line 702, in run_through_rpc
@@ -2605,7 +2605,7 @@ tvm._ffi.base.TVMError: Traceback (most recent call last):
15: _PyEval_EvalFrameDefault
14: 0x0000000000537c30
13: _PyObject_FastCallKeywords
- 12: 0x00007f76e5b7efa2
+ 12: 0x00007fca663f5fa2
11: _ctypes_callproc
10: ffi_call
9: ffi_call_unix64
@@ -2670,7 +2670,7 @@ Traceback (most recent call last):
21: _PyFunction_FastCallKeywords
20: _PyEval_EvalFrameDefault
19: _PyFunction_FastCall [('tile_f', [-1, 8, 2, 16]), ('tile_y', [-1, 7, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 1, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 0), ('unroll_explicit', 1)],None,6390073
-No: 20 GFLOPS: 145.05/145.05 result: MeasureResult(costs=(0.0015960395800000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4159400463104248, timestamp=1655777086.052862) [('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: 143.94/143.94 result: MeasureResult(costs=(0.00160826286,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.4292681217193604, timestamp=1655836758.2018938) [('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
</pre></div>
</div>
<p>Finally we can inspect the best config from log file, check correctness,
@@ -2711,7 +2711,7 @@ and measure running time.</p>
Best config:
[('tile_f', [-1, 1, 4, 1]), ('tile_y', [-1, 1, 1, 1]), ('tile_x', [-1, 7, 1, 1]), ('tile_rc', [-1, 4, 1]), ('tile_ry', [-1, 1, 1]), ('tile_rx', [-1, 1, 3]), ('auto_unroll_max_step', 1500), ('unroll_explicit', 1)],None,9881539
Finish loading 20 records
-Time cost of this operator: 0.002028
+Time cost of this operator: 0.001999
</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 3fd6cd5b8..6a83c019c 100644
--- a/docs/how_to/work_with_microtvm/micro_autotune.html
+++ b/docs/how_to/work_with_microtvm/micro_autotune.html
@@ -559,10 +559,10 @@ the tuned operator.</p>
########## Build without Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 315.9 98.72 (1, 2, 10, 10, 3) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.153 0.985 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.943 0.295 (1, 1, 10, 10, 3) 1 1
-Total_time - 319.996 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 318.2 98.758 (1, 2, 10, 10, 3) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 3.073 0.954 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.93 0.289 (1, 1, 10, 10, 3) 1 1
+Total_time - 322.202 - - - -
</pre></div>
</div>
</div>
@@ -615,10 +615,10 @@ Total_time -
########## Build with Autotuning ##########
Node Name Ops Time(us) Time(%) Shape Inputs Outputs
--------- --- -------- ------- ----- ------ -------
-tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 153.5 98.305 (1, 6, 10, 10, 1) 2 1
-tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.724 1.104 (1, 6, 10, 10) 1 1
-tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.923 0.591 (1, 1, 10, 10, 3) 1 1
-Total_time - 156.147 - - - -
+tvmgen_default_fused_nn_contrib_conv2d_NCHWc tvmgen_default_fused_nn_contrib_conv2d_NCHWc 120.4 97.847 (1, 6, 10, 10, 1) 2 1
+tvmgen_default_fused_layout_transform_1 tvmgen_default_fused_layout_transform_1 1.748 1.421 (1, 6, 10, 10) 1 1
+tvmgen_default_fused_layout_transform tvmgen_default_fused_layout_transform 0.901 0.732 (1, 1, 10, 10, 3) 1 1
+Total_time - 123.049 - - - -
</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 f784e27e2..078fca33a 100644
--- a/docs/how_to/work_with_microtvm/micro_train.html
+++ b/docs/how_to/work_with_microtvm/micro_train.html
@@ -490,7 +490,7 @@ take about <strong>2 minutes</strong> to download the Stanford Cars, while COCO
<a href="https://docs.python.org/3/library/shutil.html#shutil.move" title="shutil.move" class="sphx-glr-backref-module-shutil sphx-glr-backref-type-py-function"><span class="n">shutil</span><span class="o">.</span><span class="n">move</span></a><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><a href="https://docs.python.org/3/library/stdtypes.html#str" title="builtins.str" class="sphx-glr-backref-module-builtins sphx-glr-backref-typ [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp905e758o/images/random'
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>'/tmp/tmp286hadhz/images/random'
</pre></div>
</div>
</div>
@@ -550,8 +550,8 @@ objects to other stuff? We can display some examples from our datasets using <co
<span class="n">plt</span><span class="o">.</span><span class="n">axis</span><span class="p">(</span><span class="s2">"off"</span><span class="p">)</span>
</pre></div>
</div>
-<img src="../../_images/sphx_glr_micro_train_001.png" srcset="../../_images/sphx_glr_micro_train_001.png" alt="[1.0, 0.0], [1.0, 0.0], [1.0, 0.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [0.0, 1.0], [1.0, 0.0], [0.0, 1.0], [1.0, 0.0]" class = "sphx-glr-single-img"/><div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>/tmp/tmp905e758o/images/target contains 8144 images
-/tmp/tmp905e758o/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/tmp286hadhz/images/target contains 8144 images
+/tmp/tmp286hadhz/images/random contains 5000 images
</pre></div>
</div>
</div>
@@ -663,13 +663,13 @@ the time on our validation set).</p>
</pre></div>
</div>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Epoch 1/3
-328/328 - 55s - loss: 0.2037 - accuracy: 0.9283 - val_loss: 0.1357 - val_accuracy: 0.9585
+328/328 - 55s - loss: 0.2344 - accuracy: 0.9208 - val_loss: 0.1605 - val_accuracy: 0.9543
Epoch 2/3
-328/328 - 52s - loss: 0.0962 - accuracy: 0.9643 - val_loss: 0.1227 - val_accuracy: 0.9664
+328/328 - 52s - loss: 0.1006 - accuracy: 0.9623 - val_loss: 0.1323 - val_accuracy: 0.9630
Epoch 3/3
-328/328 - 52s - loss: 0.0652 - accuracy: 0.9748 - val_loss: 0.1419 - val_accuracy: 0.9569
+328/328 - 52s - loss: 0.0629 - accuracy: 0.9764 - val_loss: 0.1169 - val_accuracy: 0.9660
-<keras.callbacks.History object at 0x7fce0c51fb90>
+<keras.callbacks.History object at 0x7f3940fc4a50>
</pre></div>
</div>
</div>
@@ -931,7 +931,7 @@ as intended.</p>
<p>From here, we could modify the model to read live images from the camera - we have another
Arduino tutorial for how to do that <a class="reference external" href="https://github.com/guberti/tvm-arduino-demos/tree/master/examples/person_detection">on GitHub</a>. Alternatively, we could also
<a class="reference external" href="https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_autotune.html">use TVM’s autotuning capabilities</a> to dramatically improve the model’s performance.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 12.770 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 4 minutes 53.458 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 55d9afe45..3bc7f7790 100644
--- a/docs/how_to/work_with_microtvm/sg_execution_times.html
+++ b/docs/how_to/work_with_microtvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-microtvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>04:57.854</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
+<p><strong>05:39.239</strong> total execution time for <strong>how_to_work_with_microtvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,15 +312,15 @@
</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>04:12.770</p></td>
+<td><p>04:53.458</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>00:41.738</p></td>
+<td><p>00:42.314</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>00:03.346</p></td>
+<td><p>00:03.468</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 f7527cd45..ff0f4cfbf 100644
--- a/docs/how_to/work_with_relay/sg_execution_times.html
+++ b/docs/how_to/work_with_relay/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-relay-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:11.139</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
+<p><strong>00:11.377</strong> total execution time for <strong>how_to_work_with_relay</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="using_external_lib.html#sphx-glr-how-to-work-with-relay-using-external-lib-py"><span class="std std-ref">Using External Libraries in Relay</span></a> (<code class="docutils literal notranslate"><span class="pre">using_external_lib.py</span></code>)</p></td>
-<td><p>00:09.631</p></td>
+<td><p>00:09.846</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>00:01.503</p></td>
+<td><p>00:01.524</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 c81fed032..6964ea359 100644
--- a/docs/how_to/work_with_schedules/intrin_math.html
+++ b/docs/how_to/work_with_schedules/intrin_math.html
@@ -496,7 +496,7 @@ The following example customizes CUDA lowering rule for <code class="code docuti
<a href="../../reference/api/python/ir.html#tvm.ir.register_intrin_lowering" title="tvm.ir.register_intrin_lowering" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-function"><span class="n">register_intrin_lowering</span></a><span class="p">(</span><span class="s2">"tir.exp"</span><span class="p">,</span> <span class="n">target</span><span class="o">=</span><span class="s2">"cuda"</span><span class="p">,</span> <span class="n">f</span><span class="o">= [...]
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7fcd8a7414d0>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span><function my_cuda_math_rule at 0x7f3ac24e6320>
</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 5bb2775cf..a8ecbb22f 100644
--- a/docs/how_to/work_with_schedules/sg_execution_times.html
+++ b/docs/how_to/work_with_schedules/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-how-to-work-with-schedules-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.876</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
+<p><strong>00:04.203</strong> total execution time for <strong>how_to_work_with_schedules</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 83%" />
@@ -312,23 +312,23 @@
</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>00:01.808</p></td>
+<td><p>00:01.964</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tensorize.html#sphx-glr-how-to-work-with-schedules-tensorize-py"><span class="std std-ref">Use Tensorize to Leverage Hardware Intrinsics</span></a> (<code class="docutils literal notranslate"><span class="pre">tensorize.py</span></code>)</p></td>
-<td><p>00:00.911</p></td>
+<td><p>00:00.997</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>00:00.500</p></td>
+<td><p>00:00.545</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>00:00.485</p></td>
+<td><p>00:00.524</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>00:00.099</p></td>
+<td><p>00:00.100</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>
@@ -340,7 +340,7 @@
<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>00:00.012</p></td>
+<td><p>00:00.013</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 e873a7be2..c72a650cd 100644
--- a/docs/how_to/work_with_schedules/tensorize.html
+++ b/docs/how_to/work_with_schedules/tensorize.html
@@ -552,7 +552,7 @@ The importing needs to happen before the tensorized GEMV being executed.</p>
C: Buffer(C_2: Pointer(float32), float32, [524288], [])}
buffer_map = {A_1: A, B_1: B, C_1: C}
preflattened_buffer_map = {A_1: A_3: Buffer(A_2, float32, [1024, 64], []), B_1: B_3: Buffer(B_2, float32, [512, 64], []), C_1: C_3: Buffer(C_2, float32, [1024, 512], [])} {
- attr [IterVar(i: int32, (nullptr), "DataPar", "")] "pragma_import_llvm" = "; ModuleID = '/tmp/tmpcvovfugm/input0.cc'\nsource_filename = \"/tmp/tmpcvovfugm/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/tmp9i0lwnq6/input0.cc'\nsource_filename = \"/tmp/tmp9i0lwnq6/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 709f08d5f..99fb4b644 100644
--- a/docs/reference/api/python/auto_scheduler.html
+++ b/docs/reference/api/python/auto_scheduler.html
@@ -1718,7 +1718,7 @@ Can be the a function or the function name.</p></li>
<dl class="py function">
<dt class="sig sig-object py" id="tvm.auto_scheduler.auto_schedule">
-<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
+<span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">auto_schedule</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">search_policy</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em clas [...]
<dd><p>THIS API IS DEPRECATED.</p>
<p>Run auto scheduling search for a task.</p>
<dl class="field-list simple">
@@ -1755,7 +1755,7 @@ the initial naive schedule (state).</p>
<dl class="py class">
<dt class="sig sig-object py" id="tvm.auto_scheduler.SketchPolicy">
-<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
+<em class="property"><span class="pre">class</span> </em><span class="sig-prename descclassname"><span class="pre">tvm.auto_scheduler.</span></span><span class="sig-name descname"><span class="pre">SketchPolicy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">task</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">program_cost_model</span></span><span class="o"><span class="pre">=</span></span><span class="defau [...]
<dd><p>The search policy that searches in a hierarchical search space defined by sketches.
The policy randomly samples programs from the space defined by sketches and use evolutionary
search to fine-tune them.</p>
diff --git a/docs/reference/api/typedoc/classes/bytestreamreader.html b/docs/reference/api/typedoc/classes/bytestreamreader.html
index 3a1835fd5..6c22b8afa 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/9ff2a5e79/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L43">rpc_server.ts:43</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L42">rpc_server.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L63">rpc_server.ts:63</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L49">rpc_server.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L57">rpc_server.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 d6c97a796..c09af8542 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/9ff2a5e79/web/src/memory.ts#L223">memory.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L208">memory.ts:208</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L312">memory.ts:312</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L284">memory.ts:284</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L388">memory.ts:388</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L376">memory.ts:376</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L267">memory.ts:267</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L243">memory.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L321">memory.ts:321</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L252">memory.ts:252</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L359">memory.ts:359</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L342">memory.ts:342</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L350">memory.ts:350</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L326">memory.ts:326</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L363">memory.ts:363</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L346">memory.ts:346</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L334">memory.ts:334</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 0173b3cae..530b8152e 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/9ff2a5e79/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L260">runtime.ts:260</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L258">runtime.ts:258</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L262">runtime.ts:262</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L279">runtime.ts:279</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L270">runtime.ts:270</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 8ad8f7d0e..226f566ee 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/9ff2a5e79/web/src/runtime.ts#L202">runtime.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L200">runtime.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L198">runtime.ts:198</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L223">runtime.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L230">runtime.ts:230</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 7043a273c..660146374 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/9ff2a5e79/web/src/environment.ts#L86">environment.ts:86</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L70">environment.ts:70</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L69">environment.ts:69</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L78">environment.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L84">environment.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L105">environment.ts:105</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 eeff0ea31..ad52e3db2 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/9ff2a5e79/web/src/runtime.ts#L49">runtime.ts:49</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L46">runtime.ts:46</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L45">runtime.ts:45</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L44">runtime.ts:44</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L47">runtime.ts:47</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L76">runtime.ts:76</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L66">runtime.ts:66</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L84">runtime.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L95">runtime.ts:95</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L72">runtime.ts:72</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 061a7c2e3..023e67e02 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/9ff2a5e79/web/src/runtime.ts#L583">runtime.ts:583</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L579">runtime.ts:579</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L654">runtime.ts:654</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L597">runtime.ts:597</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L631">runtime.ts:631</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L644">runtime.ts:644</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L621">runtime.ts:621</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L609">runtime.ts:609</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 218e80cbf..e97d8f9a4 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/9ff2a5e79/web/src/runtime.ts#L692">runtime.ts:692</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L684">runtime.ts:684</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L683">runtime.ts:683</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L932">runtime.ts:932</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L994">runtime.ts:994</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L924">runtime.ts:924</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L732">runtime.ts:732</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L952">runtime.ts:952</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L816">runtime.ts:816</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L1033">runtime.ts:1033</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L846">runtime.ts:846</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L750">runtime.ts:750</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L1013">runtime.ts:1013</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L789">runtime.ts:789</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L914">runtime.ts:914</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L1134">runtime.ts:1134</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L740">runtime.ts:740</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L868">runtime.ts:868</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L857">runtime.ts:857</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L940">runtime.ts:940</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 e9d23d999..c9931bd04 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/9ff2a5e79/web/src/memory.ts#L40">memory.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L32">memory.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L33">memory.ts:33</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L154">memory.ts:154</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L90">memory.ts:90</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L97">memory.ts:97</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L74">memory.ts:74</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L81">memory.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L104">memory.ts:104</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L132">memory.ts:132</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L145">memory.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L60">memory.ts:60</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L67">memory.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L53">memory.ts:53</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L114">memory.ts:114</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L124">memory.ts:124</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/memory.ts#L175">memory.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 f980a9abe..8b78d1bea 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/9ff2a5e79/web/src/runtime.ts#L504">runtime.ts:504</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L502">runtime.ts:502</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L516">runtime.ts:516</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L530">runtime.ts:530</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L561">runtime.ts:561</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 7b4518780..511fb42c3 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/9ff2a5e79/web/src/runtime.ts#L304">runtime.ts:304</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L297">runtime.ts:297</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L293">runtime.ts:293</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L289">runtime.ts:289</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L291">runtime.ts:291</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L295">runtime.ts:295</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L370">runtime.ts:370</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L414">runtime.ts:414</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L355">runtime.ts:355</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L474">runtime.ts:474</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L443">runtime.ts:443</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 11fc2e50a..cfb9b1a79 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/9ff2a5e79/web/src/runtime.ts#L158">runtime.ts:158</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L157">runtime.ts:157</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L165">runtime.ts:165</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 41965c93d..b5c197a20 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/9ff2a5e79/web/src/rpc_server.ts#L92">rpc_server.ts:92</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L82">rpc_server.ts:82</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L78">rpc_server.ts:78</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L81">rpc_server.ts:81</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L79">rpc_server.ts:79</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L80">rpc_server.ts:80</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L77">rpc_server.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 9bdd1cc17..4aae8fa04 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/9ff2a5e79/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L145">runtime.ts:145</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L143">runtime.ts:143</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 9d8c8c38e..0ea26839d 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/9ff2a5e79/web/src/webgpu.ts#L57">webgpu.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L50">webgpu.ts:50</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L51">webgpu.ts:51</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L84">webgpu.ts:84</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L170">webgpu.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L67">webgpu.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 cf6e3a122..98a2e96c2 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/9ff2a5e79/web/src/ctypes.ts#L220">ctypes.ts:220</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L216">ctypes.ts:216</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L214">ctypes.ts:214</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L218">ctypes.ts:218</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L226">ctypes.ts:226</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L221">ctypes.ts:221</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L219">ctypes.ts:219</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L223">ctypes.ts:223</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L227">ctypes.ts:227</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L222">ctypes.ts:222</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L228">ctypes.ts:228</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L217">ctypes.ts:217</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L224">ctypes.ts:224</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L225">ctypes.ts:225</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L215">ctypes.ts:215</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 82f498916..35d16dba7 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/9ff2a5e79/web/src/runtime.ts#L676">runtime.ts:676</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L675">runtime.ts:675</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 f7d65ae34..ad4e228e3 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/9ff2a5e79/web/src/runtime.ts#L242">runtime.ts:242</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L240">runtime.ts:240</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L243">runtime.ts:243</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L241">runtime.ts:241</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 284091e7c..5bd3646ba 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/9ff2a5e79/web/src/rpc_server.ts#L27">rpc_server.ts:27</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L28">rpc_server.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L29">rpc_server.ts:29</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L32">rpc_server.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L31">rpc_server.ts:31</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L30">rpc_server.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 37f951531..6c43366e8 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/9ff2a5e79/web/src/ctypes.ts#L206">ctypes.ts:206</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L207">ctypes.ts:207</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L203">ctypes.ts:203</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L204">ctypes.ts:204</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L201">ctypes.ts:201</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L202">ctypes.ts:202</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L205">ctypes.ts:205</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L200">ctypes.ts:200</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L199">ctypes.ts:199</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 1cd2c799c..b4eeadada 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/9ff2a5e79/web/src/ctypes.ts#L112">ctypes.ts:112</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L128">ctypes.ts:128</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L144">ctypes.ts:144</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L136">ctypes.ts:136</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L121">ctypes.ts:121</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L160">ctypes.ts:160</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L77">ctypes.ts:77</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L83">ctypes.ts:83</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L67">ctypes.ts:67</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L57">ctypes.ts:57</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L100">ctypes.ts:100</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L88">ctypes.ts:88</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L94">ctypes.ts:94</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L34">ctypes.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L52">ctypes.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L42">ctypes.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L48">ctypes.ts:48</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L150">ctypes.ts:150</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L167">ctypes.ts:167</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L170">ctypes.ts:170</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L187">ctypes.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L179">ctypes.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L193">ctypes.ts:193</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L25">webgpu.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L36">runtime.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L25">ctypes.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/ctypes.ts#L28">ctypes.ts:28</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/rpc_server.ts#L36">rpc_server.ts:36</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/support.ts#L25">support.ts:25</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/support.ts#L39">support.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/support.ts#L52">support.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/compact.ts#L38">compact.ts:38</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L30">webgpu.ts:30</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/environment.ts#L32">environment.ts:32</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/compact.ts#L24">compact.ts:24</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L1356">runtime.ts:1356</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/support.ts#L62">support.ts:62</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L246">runtime.ts:246</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L247">runtime.ts:247</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L248">runtime.ts:248</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L249">runtime.ts:249</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L250">runtime.ts:250</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L175">runtime.ts:175</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L176">runtime.ts:176</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L180">runtime.ts:180</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L177">runtime.ts:177</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L178">runtime.ts:178</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L179">runtime.ts:179</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L183">runtime.ts:183</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L186">runtime.ts:186</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L184">runtime.ts:184</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L185">runtime.ts:185</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L189">runtime.ts:189</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L187">runtime.ts:187</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L188">runtime.ts:188</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/runtime.ts#L190">runtime.ts:190</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 d7be8fe29..2cedf9f1f 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/9ff2a5e79/web/src/types.ts#L52">types.ts:52</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 323d720cd..2dbba3193 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/9ff2a5e79/web/src/webgpu.ts#L41">webgpu.ts:41</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L42">webgpu.ts:42</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/webgpu.ts#L40">webgpu.ts:40</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 0791ebcd9..95eb756b2 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/9ff2a5e79/web/src/types.ts#L34">types.ts:34</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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/9ff2a5e79/web/src/types.ts#L39">types.ts:39</a></li>
+ <li>Defined in <a href="https://github.com/apache/tvm/blob/9e58af2ab/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 50ab7c0bb..863f9be3d 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 c252cd5e5..fc2bcb995 100644
--- a/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/autotvm/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-autotvm-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:20.656</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
+<p><strong>00:21.004</strong> total execution time for <strong>topic_vta_tutorials_autotvm</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 82%" />
@@ -312,7 +312,7 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="tune_relay_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-relay-vta-py"><span class="std std-ref">Auto-tuning a convolutional network on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_relay_vta.py</span></code>)</p></td>
-<td><p>00:20.650</p></td>
+<td><p>00:20.997</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="tune_alu_vta.html#sphx-glr-topic-vta-tutorials-autotvm-tune-alu-vta-py"><span class="std std-ref">Auto-tuning a ALU fused op on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">tune_alu_vta.py</span></code>)</p></td>
diff --git a/docs/topic/vta/tutorials/frontend/deploy_classification.html b/docs/topic/vta/tutorials/frontend/deploy_classification.html
index a4ceb31f3..413cc9db3 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_classification.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_classification.html
@@ -547,7 +547,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
DeprecationWarning,
/workspace/vta/tutorials/frontend/deploy_classification.py:213: DeprecationWarning: legacy graph executor behavior of producing json / lib / params will be removed in the next release. Please see documents of tvm.contrib.graph_executor.GraphModule for the new recommended usage.
relay_prog, target=tvm.target.Target(target, host=env.target_host), params=params
-resnet18_v1 inference graph built in 22.27s!
+resnet18_v1 inference graph built in 23.30s!
</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 b363730b9..4738f9a5d 100644
--- a/docs/topic/vta/tutorials/frontend/deploy_detection.html
+++ b/docs/topic/vta/tutorials/frontend/deploy_detection.html
@@ -565,7 +565,7 @@ and dense layer which will both be executed in fp32 on the CPU.</p></li>
"target_host parameter is going to be deprecated. "
/workspace/python/tvm/relay/build_module.py:389: DeprecationWarning: Please use input parameter mod (tvm.IRModule) instead of deprecated parameter mod (tvm.relay.function.Function)
DeprecationWarning,
-yolov3-tiny inference graph built in 15.42s!
+yolov3-tiny inference graph built in 15.96s!
</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 af87b7cb9..a500d7d69 100644
--- a/docs/topic/vta/tutorials/frontend/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/frontend/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-frontend-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>01:29.982</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
+<p><strong>01:31.727</strong> total execution time for <strong>topic_vta_tutorials_frontend</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="deploy_detection.html#sphx-glr-topic-vta-tutorials-frontend-deploy-detection-py"><span class="std std-ref">Deploy Pretrained Vision Detection Model from Darknet on VTA</span></a> (<code class="docutils literal notranslate"><span class="pre">deploy_detection.py</span></code>)</p></td>
-<td><p>00:47.321</p></td>
+<td><p>00:48.025</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>00:42.660</p></td>
+<td><p>00:43.702</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 4463852f8..2e3c6809d 100644
--- a/docs/topic/vta/tutorials/optimize/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/optimize/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-optimize-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:03.131</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
+<p><strong>00:03.274</strong> total execution time for <strong>topic_vta_tutorials_optimize</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 84%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="convolution_opt.html#sphx-glr-topic-vta-tutorials-optimize-convolution-opt-py"><span class="std std-ref">2D Convolution Optimization</span></a> (<code class="docutils literal notranslate"><span class="pre">convolution_opt.py</span></code>)</p></td>
-<td><p>00:02.768</p></td>
+<td><p>00:02.869</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="matrix_multiply_opt.html#sphx-glr-topic-vta-tutorials-optimize-matrix-multiply-opt-py"><span class="std std-ref">Matrix Multiply Blocking</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply_opt.py</span></code>)</p></td>
-<td><p>00:00.363</p></td>
+<td><p>00:00.405</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 44b0073c9..231b35597 100644
--- a/docs/topic/vta/tutorials/sg_execution_times.html
+++ b/docs/topic/vta/tutorials/sg_execution_times.html
@@ -303,7 +303,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-topic-vta-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline">¶</a></h1>
-<p><strong>00:00.636</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
+<p><strong>00:00.709</strong> total execution time for <strong>topic_vta_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 81%" />
@@ -312,11 +312,11 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="matrix_multiply.html#sphx-glr-topic-vta-tutorials-matrix-multiply-py"><span class="std std-ref">Simple Matrix Multiply</span></a> (<code class="docutils literal notranslate"><span class="pre">matrix_multiply.py</span></code>)</p></td>
-<td><p>00:00.331</p></td>
+<td><p>00:00.367</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>00:00.305</p></td>
+<td><p>00:00.342</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 6da26f796..af2ce6c47 100644
--- a/docs/tutorial/auto_scheduler_matmul_x86.html
+++ b/docs/tutorial/auto_scheduler_matmul_x86.html
@@ -455,6 +455,9 @@ trials, we can load the best schedule from the log file and apply it.</p>
<a href="../reference/api/python/te.html#tvm.te.Schedule" title="tvm.te.Schedule" class="sphx-glr-backref-module-tvm-te sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">sch</span></a><span class="p">,</span> <a href="../reference/api/python/ir.html#tvm.ir.Array" title="tvm.ir.Array" class="sphx-glr-backref-module-tvm-ir sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">args</span></a> <span class="o">=</span> <a href="../reference/api/pyth [...]
</pre></div>
</div>
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>*E
+</pre></div>
+</div>
</div>
<div class="section" id="inspecting-the-optimized-schedule">
<h2>Inspecting the Optimized Schedule<a class="headerlink" href="#inspecting-the-optimized-schedule" title="Permalink to this headline">¶</a></h2>
@@ -542,7 +545,7 @@ operator fusion.</p>
<span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 94.076 ms
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time of this operator: 92.865 ms
</pre></div>
</div>
</div>
diff --git a/docs/tutorial/autotvm_matmul_x86.html b/docs/tutorial/autotvm_matmul_x86.html
index e9c4b54db..c662d4d5a 100644
--- a/docs/tutorial/autotvm_matmul_x86.html
+++ b/docs/tutorial/autotvm_matmul_x86.html
@@ -641,16 +641,16 @@ reduce variance, we take 5 measurements and average them.</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>waiting for device...
device available
Get devices for measurement successfully!
-No: 1 GFLOPS: 10.52/10.52 result: MeasureResult(costs=(0.025526263,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5412285327911377, timestamp=1655775952.9237235) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
-No: 2 GFLOPS: 2.86/10.52 result: MeasureResult(costs=(0.0938034704,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6478667259216309, timestamp=1655775955.076716) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
-No: 3 GFLOPS: 11.88/11.88 result: MeasureResult(costs=(0.0225954924,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5553779602050781, timestamp=1655775956.0894291) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
-No: 4 GFLOPS: 1.87/11.88 result: MeasureResult(costs=(0.14390811220000002,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4246935844421387, timestamp=1655775959.0420928) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
-No: 5 GFLOPS: 3.69/11.88 result: MeasureResult(costs=(0.07265601299999999,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3002738952636719, timestamp=1655775960.4691656) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
-No: 6 GFLOPS: 1.77/11.88 result: MeasureResult(costs=(0.1514975422,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.596282720565796, timestamp=1655775963.1097283) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
-No: 7 GFLOPS: 0.82/11.88 result: MeasureResult(costs=(0.3285156574,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.366232395172119, timestamp=1655775968.522458) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
-No: 8 GFLOPS: 10.69/11.88 result: MeasureResult(costs=(0.0251015612,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5441286563873291, timestamp=1655775969.0876489) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
-No: 9 GFLOPS: 1.79/11.88 result: MeasureResult(costs=(0.1499999786,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.4982388019561768, timestamp=1655775971.703007) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
-No: 10 GFLOPS: 2.52/11.88 result: MeasureResult(costs=(0.10644707900000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.806854009628296, timestamp=1655775973.5695636) [('tile_y', [-1, 4]), ('tile_x', [-1, 4])],None,22
+No: 1 GFLOPS: 8.77/8.77 result: MeasureResult(costs=(0.0306049692,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.6216588020324707, timestamp=1655835562.5031402) [('tile_y', [-1, 1]), ('tile_x', [-1, 256])],None,80
+No: 2 GFLOPS: 2.51/8.77 result: MeasureResult(costs=(0.107064644,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.8577520847320557, timestamp=1655835564.3776634) [('tile_y', [-1, 4]), ('tile_x', [-1, 8])],None,32
+No: 3 GFLOPS: 11.79/11.79 result: MeasureResult(costs=(0.0227650914,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5546836853027344, timestamp=1655835565.4025822) [('tile_y', [-1, 64]), ('tile_x', [-1, 32])],None,56
+No: 4 GFLOPS: 1.46/11.79 result: MeasureResult(costs=(0.1833495256,), error_no=MeasureErrorNo.NO_ERROR, all_cost=3.042811870574951, timestamp=1655835568.992751) [('tile_y', [-1, 1]), ('tile_x', [-1, 4])],None,20
+No: 5 GFLOPS: 3.65/11.79 result: MeasureResult(costs=(0.07353091120000001,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.3120806217193604, timestamp=1655835570.4362006) [('tile_y', [-1, 256]), ('tile_x', [-1, 16])],None,48
+No: 6 GFLOPS: 1.79/11.79 result: MeasureResult(costs=(0.15037857459999998,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.565373420715332, timestamp=1655835573.048497) [('tile_y', [-1, 512]), ('tile_x', [-1, 4])],None,29
+No: 7 GFLOPS: 0.87/11.79 result: MeasureResult(costs=(0.307675731,), error_no=MeasureErrorNo.NO_ERROR, all_cost=5.04430627822876, timestamp=1655835578.640404) [('tile_y', [-1, 512]), ('tile_x', [-1, 2])],None,19
+No: 8 GFLOPS: 10.55/11.79 result: MeasureResult(costs=(0.025443531400000004,), error_no=MeasureErrorNo.NO_ERROR, all_cost=0.5576968193054199, timestamp=1655835579.2221763) [('tile_y', [-1, 4]), ('tile_x', [-1, 64])],None,62
+No: 9 GFLOPS: 1.90/11.79 result: MeasureResult(costs=(0.1416071596,), error_no=MeasureErrorNo.NO_ERROR, all_cost=2.3655643463134766, timestamp=1655835581.709819) [('tile_y', [-1, 2]), ('tile_x', [-1, 2])],None,11
+No: 10 GFLOPS: 2.74/11.79 result: MeasureResult(costs=(0.0980331616,), error_no=MeasureErrorNo.NO_ERROR, all_cost=1.6731891632080078, timestamp=1655835583.4421256) [('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 99fce68d4..53843ccb1 100644
--- a/docs/tutorial/autotvm_relay_x86.html
+++ b/docs/tutorial/autotvm_relay_x86.html
@@ -523,7 +523,7 @@ standard deviation.</p>
<span class="nb">print</span><span class="p">(</span><a href="https://docs.python.org/3/library/stdtypes.html#dict" title="builtins.dict" class="sphx-glr-backref-module-builtins sphx-glr-backref-type-py-class sphx-glr-backref-instance"><span class="n">unoptimized</span></a><span class="p">)</span>
</pre></div>
</div>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.62848814001154, 'median': 493.2573527999921, 'std': 0.9040261763734981}
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>{'mean': 493.3181805199956, 'median': 493.2952068499844, 'std': 0.8367690376909532}
</pre></div>
</div>
</div>
@@ -678,179 +678,179 @@ depending on the specifics of the model and the target platform.</p>
"target_host parameter is going to be deprecated. "
[Task 1/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 1/25] Current/Best: 17.52/ 17.52 GFLOPS | Progress: (4/20) | 5.96 s
-[Task 1/25] Current/Best: 6.16/ 17.52 GFLOPS | Progress: (8/20) | 8.89 s
-[Task 1/25] Current/Best: 11.51/ 22.48 GFLOPS | Progress: (12/20) | 11.31 s
-[Task 1/25] Current/Best: 16.85/ 22.77 GFLOPS | Progress: (16/20) | 12.99 s
-[Task 1/25] Current/Best: 11.57/ 23.92 GFLOPS | Progress: (20/20) | 14.71 s Done.
+[Task 1/25] Current/Best: 17.35/ 17.35 GFLOPS | Progress: (4/20) | 6.15 s
+[Task 1/25] Current/Best: 6.15/ 17.35 GFLOPS | Progress: (8/20) | 9.13 s
+[Task 1/25] Current/Best: 11.50/ 22.73 GFLOPS | Progress: (12/20) | 11.57 s
+[Task 1/25] Current/Best: 16.78/ 22.73 GFLOPS | Progress: (16/20) | 13.25 s
+[Task 1/25] Current/Best: 11.59/ 23.86 GFLOPS | Progress: (20/20) | 14.99 s Done.
[Task 2/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 2/25] Current/Best: 12.17/ 13.21 GFLOPS | Progress: (4/20) | 3.69 s
-[Task 2/25] Current/Best: 14.25/ 18.84 GFLOPS | Progress: (8/20) | 4.97 s
-[Task 2/25] Current/Best: 21.21/ 21.21 GFLOPS | Progress: (12/20) | 6.28 s
-[Task 2/25] Current/Best: 12.57/ 21.21 GFLOPS | Progress: (16/20) | 7.56 s
-[Task 2/25] Current/Best: 20.08/ 21.21 GFLOPS | Progress: (20/20) | 9.10 s Done.
+[Task 2/25] Current/Best: 12.02/ 13.05 GFLOPS | Progress: (4/20) | 3.78 s
+[Task 2/25] Current/Best: 14.12/ 17.74 GFLOPS | Progress: (8/20) | 5.09 s
+[Task 2/25] Current/Best: 20.91/ 20.91 GFLOPS | Progress: (12/20) | 6.41 s
+[Task 2/25] Current/Best: 11.87/ 20.91 GFLOPS | Progress: (16/20) | 7.68 s
+[Task 2/25] Current/Best: 19.47/ 20.91 GFLOPS | Progress: (20/20) | 9.31 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/ 10.56 GFLOPS | Progress: (4/20) | 5.78 s
-[Task 3/25] Current/Best: 15.61/ 16.88 GFLOPS | Progress: (8/20) | 7.71 s
-[Task 3/25] Current/Best: 14.90/ 16.88 GFLOPS | Progress: (12/20) | 9.44 s
-[Task 3/25] Current/Best: 7.20/ 22.06 GFLOPS | Progress: (16/20) | 11.38 s
-[Task 3/25] Current/Best: 12.47/ 22.06 GFLOPS | Progress: (20/20) | 15.91 s Done.
+[Task 3/25] Current/Best: 1.63/ 10.57 GFLOPS | Progress: (4/20) | 5.85 s
+[Task 3/25] Current/Best: 15.49/ 16.86 GFLOPS | Progress: (8/20) | 7.76 s
+[Task 3/25] Current/Best: 14.87/ 16.86 GFLOPS | Progress: (12/20) | 9.51 s
+[Task 3/25] Current/Best: 7.17/ 23.72 GFLOPS | Progress: (16/20) | 11.45 s
+[Task 3/25] Current/Best: 12.63/ 23.72 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: 9.55/ 20.48 GFLOPS | Progress: (4/20) | 2.32 s
-[Task 4/25] Current/Best: 6.86/ 20.48 GFLOPS | Progress: (8/20) | 6.60 s
-[Task 4/25] Current/Best: 21.97/ 21.97 GFLOPS | Progress: (12/20) | 10.99 s
-[Task 4/25] Current/Best: 17.42/ 21.97 GFLOPS | Progress: (16/20) | 13.18 s
-[Task 4/25] Current/Best: 13.18/ 21.97 GFLOPS | Progress: (20/20) | 15.17 s Done.
+[Task 4/25] Current/Best: 9.42/ 19.97 GFLOPS | Progress: (4/20) | 2.35 s
+[Task 4/25] Current/Best: 6.88/ 19.97 GFLOPS | Progress: (8/20) | 6.74 s
+[Task 4/25] Current/Best: 21.89/ 21.89 GFLOPS | Progress: (12/20) | 11.25 s
+[Task 4/25] Current/Best: 17.26/ 21.89 GFLOPS | Progress: (16/20) | 13.51 s
+[Task 4/25] Current/Best: 13.14/ 21.89 GFLOPS | Progress: (20/20) | 15.43 s Done.
[Task 5/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 5/25] Current/Best: 9.85/ 10.15 GFLOPS | Progress: (4/20) | 2.54 s
-[Task 5/25] Current/Best: 11.61/ 11.87 GFLOPS | Progress: (8/20) | 4.59 s
-[Task 5/25] Current/Best: 11.56/ 18.09 GFLOPS | Progress: (12/20) | 7.69 s
-[Task 5/25] Current/Best: 11.81/ 22.80 GFLOPS | Progress: (16/20) | 9.10 s
-[Task 5/25] Current/Best: 11.92/ 22.80 GFLOPS | Progress: (20/20) | 10.95 s Done.
+[Task 5/25] Current/Best: 9.50/ 10.19 GFLOPS | Progress: (4/20) | 2.57 s
+[Task 5/25] Current/Best: 11.51/ 12.65 GFLOPS | Progress: (8/20) | 4.65 s
+[Task 5/25] Current/Best: 11.11/ 18.14 GFLOPS | Progress: (12/20) | 7.78 s
+[Task 5/25] Current/Best: 11.66/ 22.64 GFLOPS | Progress: (16/20) | 9.24 s
+[Task 5/25] Current/Best: 11.16/ 22.64 GFLOPS | Progress: (20/20) | 11.14 s Done.
[Task 6/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 6/25] Current/Best: 12.28/ 20.78 GFLOPS | Progress: (4/20) | 3.92 s
-[Task 6/25] Current/Best: 18.92/ 20.78 GFLOPS | Progress: (8/20) | 5.68 s
-[Task 6/25] Current/Best: 13.34/ 20.78 GFLOPS | Progress: (12/20) | 7.60 s
-[Task 6/25] Current/Best: 19.98/ 20.78 GFLOPS | Progress: (16/20) | 9.85 s
-[Task 6/25] Current/Best: 3.72/ 20.78 GFLOPS | Progress: (20/20) | 12.35 s Done.
+[Task 6/25] Current/Best: 12.24/ 20.85 GFLOPS | Progress: (4/20) | 4.01 s
+[Task 6/25] Current/Best: 18.96/ 20.85 GFLOPS | Progress: (8/20) | 5.79 s
+[Task 6/25] Current/Best: 13.28/ 20.85 GFLOPS | Progress: (12/20) | 7.73 s
+[Task 6/25] Current/Best: 20.01/ 20.85 GFLOPS | Progress: (16/20) | 10.00 s
+[Task 6/25] Current/Best: 3.66/ 20.85 GFLOPS | Progress: (20/20) | 12.53 s Done.
[Task 7/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 7/25] Current/Best: 11.16/ 12.96 GFLOPS | Progress: (4/20) | 3.56 s
-[Task 7/25] Current/Best: 20.28/ 21.12 GFLOPS | Progress: (8/20) | 5.05 s
-[Task 7/25] Current/Best: 15.83/ 21.12 GFLOPS | Progress: (12/20) | 6.98 s
-[Task 7/25] Current/Best: 12.26/ 21.12 GFLOPS | Progress: (16/20) | 9.02 s
-[Task 7/25] Current/Best: 6.30/ 21.72 GFLOPS | Progress: (20/20) | 11.47 s Done.
+[Task 7/25] Current/Best: 10.63/ 12.15 GFLOPS | Progress: (4/20) | 3.53 s
+[Task 7/25] Current/Best: 20.22/ 20.88 GFLOPS | Progress: (8/20) | 5.04 s
+[Task 7/25] Current/Best: 16.11/ 20.88 GFLOPS | Progress: (12/20) | 6.94 s
+[Task 7/25] Current/Best: 12.22/ 20.88 GFLOPS | Progress: (16/20) | 9.00 s
+[Task 7/25] Current/Best: 6.26/ 21.69 GFLOPS | Progress: (20/20) | 11.44 s Done.
[Task 8/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 8/25] Current/Best: 10.08/ 14.01 GFLOPS | Progress: (4/20) | 2.83 s
-[Task 8/25] Current/Best: 9.33/ 14.01 GFLOPS | Progress: (8/20) | 7.61 s
-[Task 8/25] Current/Best: 12.60/ 14.01 GFLOPS | Progress: (12/20) | 13.66 s
-[Task 8/25] Current/Best: 18.65/ 18.65 GFLOPS | Progress: (16/20) | 15.74 s
-[Task 8/25] Current/Best: 19.99/ 19.99 GFLOPS | Progress: (20/20) | 22.26 s Done.
+[Task 8/25] Current/Best: 9.61/ 13.80 GFLOPS | Progress: (4/20) | 2.90 s
+[Task 8/25] Current/Best: 9.04/ 13.80 GFLOPS | Progress: (8/20) | 7.69 s
+[Task 8/25] Current/Best: 12.54/ 13.80 GFLOPS | Progress: (12/20) | 13.79 s
+[Task 8/25] Current/Best: 18.88/ 18.88 GFLOPS | Progress: (16/20) | 15.90 s
+[Task 8/25] Current/Best: 19.52/ 19.52 GFLOPS | Progress: (20/20) | 22.57 s Done.
[Task 9/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 9/25] Current/Best: 14.31/ 15.53 GFLOPS | Progress: (4/20) | 11.88 s
-[Task 9/25] Current/Best: 23.37/ 23.37 GFLOPS | Progress: (8/20) | 13.63 s
-[Task 9/25] Current/Best: 8.29/ 23.37 GFLOPS | Progress: (12/20) | 15.95 s
-[Task 9/25] Current/Best: 17.97/ 23.37 GFLOPS | Progress: (16/20) | 18.60 s
-[Task 9/25] Current/Best: 9.06/ 23.37 GFLOPS | Progress: (20/20) | 26.22 s
+[Task 9/25] Current/Best: 14.29/ 15.76 GFLOPS | Progress: (4/20) | 11.93 s
+[Task 9/25] Current/Best: 23.21/ 23.21 GFLOPS | Progress: (8/20) | 13.74 s
+[Task 9/25] Current/Best: 8.20/ 23.21 GFLOPS | Progress: (12/20) | 16.14 s
+[Task 9/25] Current/Best: 17.83/ 23.21 GFLOPS | Progress: (16/20) | 18.83 s
+[Task 9/25] Current/Best: 8.93/ 23.21 GFLOPS | Progress: (20/20) | 26.66 s
[Task 10/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 10/25] Current/Best: 18.14/ 18.14 GFLOPS | Progress: (4/20) | 2.51 s
-[Task 10/25] Current/Best: 15.55/ 18.14 GFLOPS | Progress: (8/20) | 4.11 s
-[Task 10/25] Current/Best: 12.23/ 18.96 GFLOPS | Progress: (12/20) | 5.63 s
-[Task 10/25] Current/Best: 19.11/ 20.34 GFLOPS | Progress: (16/20) | 6.73 s
-[Task 10/25] Current/Best: 8.87/ 20.34 GFLOPS | Progress: (20/20) | 8.26 s Done.
+[Task 10/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (4/20) | 2.55 s
+[Task 10/25] Current/Best: 15.55/ 18.20 GFLOPS | Progress: (8/20) | 4.15 s
+[Task 10/25] Current/Best: 12.36/ 18.81 GFLOPS | Progress: (12/20) | 5.69 s
+[Task 10/25] Current/Best: 19.03/ 20.30 GFLOPS | Progress: (16/20) | 6.80 s
+[Task 10/25] Current/Best: 8.79/ 20.30 GFLOPS | Progress: (20/20) | 8.33 s Done.
[Task 11/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 11/25] Current/Best: 12.25/ 18.11 GFLOPS | Progress: (4/20) | 3.22 s
-[Task 11/25] Current/Best: 16.87/ 18.11 GFLOPS | Progress: (8/20) | 5.95 s
-[Task 11/25] Current/Best: 18.10/ 18.11 GFLOPS | Progress: (12/20) | 7.96 s
-[Task 11/25] Current/Best: 13.44/ 21.16 GFLOPS | Progress: (16/20) | 10.65 s
-[Task 11/25] Current/Best: 19.39/ 21.48 GFLOPS | Progress: (20/20) | 12.66 s Done.
+[Task 11/25] Current/Best: 12.26/ 18.03 GFLOPS | Progress: (4/20) | 3.31 s
+[Task 11/25] Current/Best: 16.92/ 18.03 GFLOPS | Progress: (8/20) | 6.08 s
+[Task 11/25] Current/Best: 18.20/ 18.20 GFLOPS | Progress: (12/20) | 8.14 s
+[Task 11/25] Current/Best: 13.38/ 21.19 GFLOPS | Progress: (16/20) | 10.98 s
+[Task 11/25] Current/Best: 19.39/ 21.45 GFLOPS | Progress: (20/20) | 13.04 s Done.
[Task 12/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 12/25] Current/Best: 7.81/ 18.07 GFLOPS | Progress: (4/20) | 5.27 s
-[Task 12/25] Current/Best: 5.29/ 18.07 GFLOPS | Progress: (8/20) | 8.92 s
-[Task 12/25] Current/Best: 19.03/ 19.03 GFLOPS | Progress: (12/20) | 10.88 s
-[Task 12/25] Current/Best: 15.38/ 19.03 GFLOPS | Progress: (16/20) | 13.66 s
-[Task 12/25] Current/Best: 15.18/ 19.03 GFLOPS | Progress: (20/20) | 15.58 s Done.
+[Task 12/25] Current/Best: 7.74/ 18.08 GFLOPS | Progress: (4/20) | 5.48 s
+[Task 12/25] Current/Best: 5.31/ 18.08 GFLOPS | Progress: (8/20) | 9.24 s
+[Task 12/25] Current/Best: 19.10/ 19.10 GFLOPS | Progress: (12/20) | 11.24 s
+[Task 12/25] Current/Best: 14.95/ 19.10 GFLOPS | Progress: (16/20) | 14.06 s
+[Task 12/25] Current/Best: 15.11/ 19.10 GFLOPS | Progress: (20/20) | 15.98 s Done.
[Task 13/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 13/25] Current/Best: 8.78/ 17.25 GFLOPS | Progress: (4/20) | 3.60 s
-[Task 13/25] Current/Best: 16.01/ 20.99 GFLOPS | Progress: (8/20) | 6.00 s
-[Task 13/25] Current/Best: 19.20/ 21.54 GFLOPS | Progress: (12/20) | 8.86 s
-[Task 13/25] Current/Best: 12.29/ 21.54 GFLOPS | Progress: (16/20) | 12.27 s
-[Task 13/25] Current/Best: 18.74/ 21.54 GFLOPS | Progress: (20/20) | 14.51 s Done.
+[Task 13/25] Current/Best: 9.04/ 17.28 GFLOPS | Progress: (4/20) | 3.69 s
+[Task 13/25] Current/Best: 15.53/ 20.73 GFLOPS | Progress: (8/20) | 6.19 s
+[Task 13/25] Current/Best: 18.98/ 21.10 GFLOPS | Progress: (12/20) | 9.13 s
+[Task 13/25] Current/Best: 12.17/ 21.10 GFLOPS | Progress: (16/20) | 12.58 s
+[Task 13/25] Current/Best: 18.15/ 21.10 GFLOPS | Progress: (20/20) | 14.83 s Done.
[Task 14/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 14/25] Current/Best: 13.67/ 13.67 GFLOPS | Progress: (4/20) | 3.18 s
-[Task 14/25] Current/Best: 6.11/ 13.67 GFLOPS | Progress: (8/20) | 5.36 s
-[Task 14/25] Current/Best: 20.57/ 20.57 GFLOPS | Progress: (12/20) | 7.91 s
-[Task 14/25] Current/Best: 17.06/ 20.57 GFLOPS | Progress: (16/20) | 9.55 s Done.
+[Task 14/25] Current/Best: 13.57/ 13.57 GFLOPS | Progress: (4/20) | 3.36 s
+[Task 14/25] Current/Best: 6.03/ 13.57 GFLOPS | Progress: (8/20) | 5.59 s
+[Task 14/25] Current/Best: 19.95/ 19.95 GFLOPS | Progress: (12/20) | 8.16 s
+[Task 14/25] Current/Best: 16.28/ 19.95 GFLOPS | Progress: (16/20) | 9.83 s Done.
-[Task 14/25] Current/Best: 17.32/ 20.57 GFLOPS | Progress: (20/20) | 11.27 s
+[Task 14/25] Current/Best: 17.25/ 19.95 GFLOPS | Progress: (20/20) | 11.55 s
[Task 15/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 15/25] Current/Best: 16.12/ 17.65 GFLOPS | Progress: (4/20) | 2.63 s
-[Task 15/25] Current/Best: 13.44/ 18.03 GFLOPS | Progress: (8/20) | 3.97 s
-[Task 15/25] Current/Best: 10.39/ 22.25 GFLOPS | Progress: (12/20) | 6.04 s
-[Task 15/25] Current/Best: 20.36/ 22.25 GFLOPS | Progress: (16/20) | 8.98 s
-[Task 15/25] Current/Best: 9.69/ 22.25 GFLOPS | Progress: (20/20) | 9.95 s
+[Task 15/25] Current/Best: 15.95/ 17.61 GFLOPS | Progress: (4/20) | 2.69 s
+[Task 15/25] Current/Best: 14.29/ 17.97 GFLOPS | Progress: (8/20) | 4.05 s
+[Task 15/25] Current/Best: 10.35/ 22.28 GFLOPS | Progress: (12/20) | 6.17 s
+[Task 15/25] Current/Best: 20.25/ 22.28 GFLOPS | Progress: (16/20) | 9.15 s
+[Task 15/25] Current/Best: 9.62/ 22.28 GFLOPS | Progress: (20/20) | 10.14 s
[Task 16/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 16/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (4/20) | 2.99 s
-[Task 16/25] Current/Best: 3.04/ 20.46 GFLOPS | Progress: (8/20) | 4.61 s
-[Task 16/25] Current/Best: 19.29/ 20.46 GFLOPS | Progress: (12/20) | 5.82 s
-[Task 16/25] Current/Best: 18.05/ 20.46 GFLOPS | Progress: (16/20) | 7.18 s
-[Task 16/25] Current/Best: 9.96/ 22.21 GFLOPS | Progress: (20/20) | 9.22 s Done.
+[Task 16/25] Current/Best: 20.50/ 20.50 GFLOPS | Progress: (4/20) | 2.92 s
+[Task 16/25] Current/Best: 3.03/ 20.50 GFLOPS | Progress: (8/20) | 4.55 s
+[Task 16/25] Current/Best: 19.23/ 20.50 GFLOPS | Progress: (12/20) | 5.78 s
+[Task 16/25] Current/Best: 17.56/ 20.50 GFLOPS | Progress: (16/20) | 7.15 s
+[Task 16/25] Current/Best: 9.97/ 22.28 GFLOPS | Progress: (20/20) | 9.24 s Done.
[Task 17/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 17/25] Current/Best: 13.51/ 18.87 GFLOPS | Progress: (4/20) | 4.68 s
-[Task 17/25] Current/Best: 14.36/ 23.23 GFLOPS | Progress: (8/20) | 7.52 s
-[Task 17/25] Current/Best: 16.87/ 23.23 GFLOPS | Progress: (12/20) | 9.54 s
-[Task 17/25] Current/Best: 16.57/ 23.23 GFLOPS | Progress: (16/20) | 11.69 s
-[Task 17/25] Current/Best: 10.04/ 23.23 GFLOPS | Progress: (20/20) | 13.81 s Done.
+[Task 17/25] Current/Best: 12.74/ 18.84 GFLOPS | Progress: (4/20) | 4.72 s
+[Task 17/25] Current/Best: 14.40/ 23.03 GFLOPS | Progress: (8/20) | 7.52 s
+[Task 17/25] Current/Best: 17.14/ 23.03 GFLOPS | Progress: (12/20) | 9.57 s
+[Task 17/25] Current/Best: 16.42/ 23.03 GFLOPS | Progress: (16/20) | 11.74 s
+[Task 17/25] Current/Best: 10.01/ 23.03 GFLOPS | Progress: (20/20) | 13.88 s Done.
[Task 18/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 18/25] Current/Best: 11.40/ 18.10 GFLOPS | Progress: (4/20) | 3.62 s
-[Task 18/25] Current/Best: 10.58/ 19.44 GFLOPS | Progress: (8/20) | 7.02 s
-[Task 18/25] Current/Best: 18.99/ 19.44 GFLOPS | Progress: (12/20) | 8.95 s
-[Task 18/25] Current/Best: 10.06/ 19.44 GFLOPS | Progress: (16/20) | 12.53 s
-[Task 18/25] Current/Best: 20.92/ 20.92 GFLOPS | Progress: (20/20) | 14.02 s Done.
+[Task 18/25] Current/Best: 11.62/ 17.68 GFLOPS | Progress: (4/20) | 3.72 s
+[Task 18/25] Current/Best: 10.63/ 19.91 GFLOPS | Progress: (8/20) | 7.25 s
+[Task 18/25] Current/Best: 19.07/ 19.91 GFLOPS | Progress: (12/20) | 9.17 s
+[Task 18/25] Current/Best: 9.97/ 19.91 GFLOPS | Progress: (16/20) | 12.85 s
+[Task 18/25] Current/Best: 20.46/ 20.46 GFLOPS | Progress: (20/20) | 14.38 s Done.
[Task 19/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 19/25] Current/Best: 7.13/ 20.33 GFLOPS | Progress: (4/20) | 5.91 s
-[Task 19/25] Current/Best: 2.61/ 20.33 GFLOPS | Progress: (8/20) | 9.17 s
-[Task 19/25] Current/Best: 19.75/ 21.73 GFLOPS | Progress: (12/20) | 11.93 s
-[Task 19/25] Current/Best: 14.23/ 21.73 GFLOPS | Progress: (16/20) | 14.75 s
-[Task 19/25] Current/Best: 2.70/ 23.47 GFLOPS | Progress: (20/20) | 17.59 s Done.
+[Task 19/25] Current/Best: 6.94/ 19.99 GFLOPS | Progress: (4/20) | 6.08 s
+[Task 19/25] Current/Best: 2.59/ 19.99 GFLOPS | Progress: (8/20) | 9.36 s
+[Task 19/25] Current/Best: 17.31/ 20.73 GFLOPS | Progress: (12/20) | 12.17 s
+[Task 19/25] Current/Best: 13.46/ 20.73 GFLOPS | Progress: (16/20) | 15.07 s
+[Task 19/25] Current/Best: 2.70/ 23.05 GFLOPS | Progress: (20/20) | 17.84 s Done.
[Task 20/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 20/25] Current/Best: 9.33/ 15.34 GFLOPS | Progress: (4/20) | 3.25 s Done.
+[Task 20/25] Current/Best: 9.01/ 14.95 GFLOPS | Progress: (4/20) | 3.32 s Done.
Done.
-[Task 20/25] Current/Best: 9.80/ 15.34 GFLOPS | Progress: (8/20) | 6.52 s
-[Task 20/25] Current/Best: 2.32/ 16.67 GFLOPS | Progress: (12/20) | 10.56 s
-[Task 20/25] Current/Best: 12.21/ 16.67 GFLOPS | Progress: (16/20) | 14.10 s
-[Task 20/25] Current/Best: 12.46/ 21.97 GFLOPS | Progress: (20/20) | 16.19 s
+[Task 20/25] Current/Best: 10.19/ 14.95 GFLOPS | Progress: (8/20) | 6.81 s
+[Task 20/25] Current/Best: 2.32/ 14.99 GFLOPS | Progress: (12/20) | 10.77 s
+[Task 20/25] Current/Best: 12.42/ 14.99 GFLOPS | Progress: (16/20) | 14.44 s
+[Task 20/25] Current/Best: 13.35/ 21.64 GFLOPS | Progress: (20/20) | 16.55 s
[Task 21/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
-[Task 21/25] Current/Best: 6.38/ 17.56 GFLOPS | Progress: (4/20) | 3.16 s
-[Task 21/25] Current/Best: 14.61/ 17.56 GFLOPS | Progress: (8/20) | 4.70 s
-[Task 21/25] Current/Best: 1.61/ 17.56 GFLOPS | Progress: (12/20) | 6.81 s
-[Task 21/25] Current/Best: 17.92/ 17.92 GFLOPS | Progress: (16/20) | 10.21 s
-[Task 21/25] Current/Best: 4.48/ 17.92 GFLOPS | Progress: (20/20) | 17.30 s
+[Task 21/25] Current/Best: 6.38/ 17.60 GFLOPS | Progress: (4/20) | 3.22 s
+[Task 21/25] Current/Best: 14.47/ 17.60 GFLOPS | Progress: (8/20) | 4.84 s
+[Task 21/25] Current/Best: 1.61/ 17.60 GFLOPS | Progress: (12/20) | 6.98 s
+[Task 21/25] Current/Best: 18.18/ 18.18 GFLOPS | Progress: (16/20) | 10.43 s
+[Task 21/25] Current/Best: 4.46/ 18.18 GFLOPS | Progress: (20/20) | 17.70 s
[Task 22/25] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/20) | 0.00 s
... 307 lines suppressed ...